Re: [PATCH 09/10] xfs: move growfs core to libxfs

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Sat, May 12, 2018 at 08:51:06AM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> So it can be shared with userspace (e.g. mkfs) easily.
> 
> Signed-Off-By: Dave Chinner <dchinner@redhat.com>

Looks ok,
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>

--D

> ---
>  fs/xfs/Makefile        |   1 +
>  fs/xfs/libxfs/xfs_ag.c | 376 ++++++++++++++++++++++++++++++++++
>  fs/xfs/libxfs/xfs_ag.h |  26 +++
>  fs/xfs/libxfs/xfs_sb.c |  73 +++++++
>  fs/xfs/libxfs/xfs_sb.h |   9 +
>  fs/xfs/xfs_fsops.c     | 452 +----------------------------------------
>  6 files changed, 489 insertions(+), 448 deletions(-)
>  create mode 100644 fs/xfs/libxfs/xfs_ag.c
>  create mode 100644 fs/xfs/libxfs/xfs_ag.h
> 
> diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
> index 7ceb41a9786a..762477208322 100644
> --- a/fs/xfs/Makefile
> +++ b/fs/xfs/Makefile
> @@ -28,6 +28,7 @@ xfs-y				+= xfs_trace.o
>  
>  # build the libxfs code first
>  xfs-y				+= $(addprefix libxfs/, \
> +				   xfs_ag.o \
>  				   xfs_alloc.o \
>  				   xfs_alloc_btree.o \
>  				   xfs_attr.o \
> diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
> new file mode 100644
> index 000000000000..638bc162afb5
> --- /dev/null
> +++ b/fs/xfs/libxfs/xfs_ag.c
> @@ -0,0 +1,376 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (c) 2000-2005 Silicon Graphics, Inc.
> + * Copyright (c) 2018 Red Hat, Inc.
> + * All rights reserved.
> + */
> +
> +#include "xfs.h"
> +#include "xfs_fs.h"
> +#include "xfs_shared.h"
> +#include "xfs_format.h"
> +#include "xfs_trans_resv.h"
> +#include "xfs_sb.h"
> +#include "xfs_mount.h"
> +#include "xfs_btree.h"
> +#include "xfs_alloc_btree.h"
> +#include "xfs_rmap_btree.h"
> +#include "xfs_alloc.h"
> +#include "xfs_rmap.h"
> +#include "xfs_ag.h"
> +
> +static struct xfs_buf *
> +xfs_get_aghdr_buf(
> +	struct xfs_mount	*mp,
> +	xfs_daddr_t		blkno,
> +	size_t			numblks,
> +	int			flags,
> +	const struct xfs_buf_ops *ops)
> +{
> +	struct xfs_buf		*bp;
> +
> +	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
> +	if (!bp)
> +		return NULL;
> +
> +	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
> +	bp->b_bn = blkno;
> +	bp->b_maps[0].bm_bn = blkno;
> +	bp->b_ops = ops;
> +
> +	return bp;
> +}
> +
> +/*
> + * Generic btree root block init function
> + */
> +static void
> +xfs_btroot_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	xfs_btree_init_block(mp, bp, id->type, 0, id->numrecs, id->agno, 0);
> +}
> +
> +/*
> + * Alloc btree root block init functions
> + */
> +static void
> +xfs_bnoroot_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_alloc_rec	*arec;
> +
> +	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0);
> +	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
> +	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
> +	arec->ar_blockcount = cpu_to_be32(id->agsize -
> +					  be32_to_cpu(arec->ar_startblock));
> +}
> +
> +static void
> +xfs_cntroot_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_alloc_rec	*arec;
> +
> +	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0);
> +	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
> +	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
> +	arec->ar_blockcount = cpu_to_be32(id->agsize -
> +					  be32_to_cpu(arec->ar_startblock));
> +}
> +
> +/*
> + * Reverse map root block init
> + */
> +static void
> +xfs_rmaproot_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
> +	struct xfs_rmap_rec	*rrec;
> +
> +	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0);
> +
> +	/*
> +	 * mark the AG header regions as static metadata The BNO
> +	 * btree block is the first block after the headers, so
> +	 * it's location defines the size of region the static
> +	 * metadata consumes.
> +	 *
> +	 * Note: unlike mkfs, we never have to account for log
> +	 * space when growing the data regions
> +	 */
> +	rrec = XFS_RMAP_REC_ADDR(block, 1);
> +	rrec->rm_startblock = 0;
> +	rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
> +	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
> +	rrec->rm_offset = 0;
> +
> +	/* account freespace btree root blocks */
> +	rrec = XFS_RMAP_REC_ADDR(block, 2);
> +	rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
> +	rrec->rm_blockcount = cpu_to_be32(2);
> +	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
> +	rrec->rm_offset = 0;
> +
> +	/* account inode btree root blocks */
> +	rrec = XFS_RMAP_REC_ADDR(block, 3);
> +	rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
> +	rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
> +					  XFS_IBT_BLOCK(mp));
> +	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
> +	rrec->rm_offset = 0;
> +
> +	/* account for rmap btree root */
> +	rrec = XFS_RMAP_REC_ADDR(block, 4);
> +	rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
> +	rrec->rm_blockcount = cpu_to_be32(1);
> +	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
> +	rrec->rm_offset = 0;
> +
> +	/* account for refc btree root */
> +	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
> +		rrec = XFS_RMAP_REC_ADDR(block, 5);
> +		rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp));
> +		rrec->rm_blockcount = cpu_to_be32(1);
> +		rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
> +		rrec->rm_offset = 0;
> +		be16_add_cpu(&block->bb_numrecs, 1);
> +	}
> +}
> +
> +/*
> + * Initialise new secondary superblocks with the pre-grow geometry, but mark
> + * them as "in progress" so we know they haven't yet been activated. This will
> + * get cleared when the update with the new geometry information is done after
> + * changes to the primary are committed. This isn't strictly necessary, but we
> + * get it for free with the delayed buffer write lists and it means we can tell
> + * if a grow operation didn't complete properly after the fact.
> + */
> +static void
> +xfs_sbblock_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
> +
> +	xfs_sb_to_disk(dsb, &mp->m_sb);
> +	dsb->sb_inprogress = 1;
> +}
> +
> +static void
> +xfs_agfblock_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_agf		*agf = XFS_BUF_TO_AGF(bp);
> +	xfs_extlen_t		tmpsize;
> +
> +	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
> +	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
> +	agf->agf_seqno = cpu_to_be32(id->agno);
> +	agf->agf_length = cpu_to_be32(id->agsize);
> +	agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
> +	agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
> +	agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
> +	agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
> +	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
> +		agf->agf_roots[XFS_BTNUM_RMAPi] =
> +					cpu_to_be32(XFS_RMAP_BLOCK(mp));
> +		agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
> +		agf->agf_rmap_blocks = cpu_to_be32(1);
> +	}
> +
> +	agf->agf_flfirst = cpu_to_be32(1);
> +	agf->agf_fllast = 0;
> +	agf->agf_flcount = 0;
> +	tmpsize = id->agsize - mp->m_ag_prealloc_blocks;
> +	agf->agf_freeblks = cpu_to_be32(tmpsize);
> +	agf->agf_longest = cpu_to_be32(tmpsize);
> +	if (xfs_sb_version_hascrc(&mp->m_sb))
> +		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
> +	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
> +		agf->agf_refcount_root = cpu_to_be32(
> +				xfs_refc_block(mp));
> +		agf->agf_refcount_level = cpu_to_be32(1);
> +		agf->agf_refcount_blocks = cpu_to_be32(1);
> +	}
> +}
> +
> +static void
> +xfs_agflblock_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_agfl		*agfl = XFS_BUF_TO_AGFL(bp);
> +	__be32			*agfl_bno;
> +	int			bucket;
> +
> +	if (xfs_sb_version_hascrc(&mp->m_sb)) {
> +		agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
> +		agfl->agfl_seqno = cpu_to_be32(id->agno);
> +		uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
> +	}
> +
> +	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
> +	for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
> +		agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
> +}
> +
> +static void
> +xfs_agiblock_init(
> +	struct xfs_mount	*mp,
> +	struct xfs_buf		*bp,
> +	struct aghdr_init_data	*id)
> +{
> +	struct xfs_agi		*agi = XFS_BUF_TO_AGI(bp);
> +	int			bucket;
> +
> +	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
> +	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
> +	agi->agi_seqno = cpu_to_be32(id->agno);
> +	agi->agi_length = cpu_to_be32(id->agsize);
> +	agi->agi_count = 0;
> +	agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
> +	agi->agi_level = cpu_to_be32(1);
> +	agi->agi_freecount = 0;
> +	agi->agi_newino = cpu_to_be32(NULLAGINO);
> +	agi->agi_dirino = cpu_to_be32(NULLAGINO);
> +	if (xfs_sb_version_hascrc(&mp->m_sb))
> +		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
> +	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
> +		agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
> +		agi->agi_free_level = cpu_to_be32(1);
> +	}
> +	for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
> +		agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
> +}
> +
> +typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,
> +				  struct aghdr_init_data *id);
> +static int
> +xfs_ag_init_hdr(
> +	struct xfs_mount	*mp,
> +	struct aghdr_init_data	*id,
> +	aghdr_init_work_f	work,
> +	const struct xfs_buf_ops *ops)
> +
> +{
> +	struct xfs_buf		*bp;
> +
> +	bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops);
> +	if (!bp)
> +		return -ENOMEM;
> +
> +	(*work)(mp, bp, id);
> +
> +	xfs_buf_delwri_queue(bp, &id->buffer_list);
> +	xfs_buf_relse(bp);
> +	return 0;
> +}
> +
> +struct xfs_aghdr_grow_data {
> +	xfs_daddr_t		daddr;
> +	size_t			numblks;
> +	const struct xfs_buf_ops *ops;
> +	aghdr_init_work_f	work;
> +	xfs_btnum_t		type;
> +	int			numrecs;
> +	bool			need_init;
> +};
> +
> +/*
> + * Prepare new AG headers to be written to disk. We use uncached buffers here,
> + * as it is assumed these new AG headers are currently beyond the currently
> + * valid filesystem address space. Using cached buffers would trip over EOFS
> + * corruption detection alogrithms in the buffer cache lookup routines.
> + *
> + * This is a non-transactional function, but the prepared buffers are added to a
> + * delayed write buffer list supplied by the caller so they can submit them to
> + * disk and wait on them as required.
> + */
> +int
> +xfs_ag_init_headers(
> +	struct xfs_mount	*mp,
> +	struct aghdr_init_data	*id)
> +
> +{
> +	struct xfs_aghdr_grow_data aghdr_data[] = {
> +		/* SB */
> +		{ XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR),
> +		  XFS_FSS_TO_BB(mp, 1), &xfs_sb_buf_ops,
> +		  &xfs_sbblock_init, 0, 0, true },
> +		/* AGF */
> +		{ XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)),
> +		  XFS_FSS_TO_BB(mp, 1), &xfs_agf_buf_ops,
> +		  &xfs_agfblock_init, 0, 0, true },
> +		/* AGFL */
> +		{ XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)),
> +		  XFS_FSS_TO_BB(mp, 1), &xfs_agfl_buf_ops,
> +		  &xfs_agflblock_init, 0, 0, true },
> +		/* AGI */
> +		{ XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)),
> +		  XFS_FSS_TO_BB(mp, 1), &xfs_agi_buf_ops,
> +		  &xfs_agiblock_init, 0, 0, true },
> +		/* BNO root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_allocbt_buf_ops,
> +		  &xfs_bnoroot_init, 0, 0, true },
> +		/* CNT root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_allocbt_buf_ops,
> +		  &xfs_cntroot_init, 0, 0, true },
> +		/* INO root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_inobt_buf_ops,
> +		  &xfs_btroot_init, XFS_BTNUM_INO, 0, true },
> +		/* FINO root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_inobt_buf_ops,
> +		  &xfs_btroot_init, XFS_BTNUM_FINO, 0,
> +		  xfs_sb_version_hasfinobt(&mp->m_sb) },
> +		/* RMAP root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_rmapbt_buf_ops,
> +		  &xfs_rmaproot_init, 0, 0,
> +		  xfs_sb_version_hasrmapbt(&mp->m_sb) },
> +		/* REFC root block */
> +		{ XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)),
> +		  BTOBB(mp->m_sb.sb_blocksize), &xfs_refcountbt_buf_ops,
> +		  &xfs_btroot_init, XFS_BTNUM_REFC, 0,
> +		  xfs_sb_version_hasreflink(&mp->m_sb) },
> +		/* NULL terminating block */
> +		{ XFS_BUF_DADDR_NULL, 0, NULL, NULL, 0, 0, false },
> +	};
> +	struct  xfs_aghdr_grow_data *dp;
> +	int			error = 0;
> +
> +	/* Account for AG free space in new AG */
> +	id->nfree += id->agsize - mp->m_ag_prealloc_blocks;
> +
> +	for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) {
> +		if (!dp->need_init)
> +			continue;
> +
> +		id->daddr = dp->daddr;
> +		id->numblks = dp->numblks;
> +		id->numrecs = dp->numrecs;
> +		id->type = dp->type;
> +		error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
> +		if (error)
> +			break;
> +	}
> +	return error;
> +}
> diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
> new file mode 100644
> index 000000000000..788f37df6610
> --- /dev/null
> +++ b/fs/xfs/libxfs/xfs_ag.h
> @@ -0,0 +1,26 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (c) 2018 Red Hat, Inc.
> + * All rights reserved.
> + */
> +
> +#ifndef __LIBXFS_AG_H
> +#define __LIBXFS_AG_H 1
> +
> +struct aghdr_init_data {
> +	/* per ag data */
> +	xfs_agblock_t		agno;		/* ag to init */
> +	xfs_extlen_t		agsize;		/* new AG size */
> +	struct list_head	buffer_list;	/* buffer writeback list */
> +	xfs_rfsblock_t		nfree;		/* cumulative new free space */
> +
> +	/* per header data */
> +	xfs_daddr_t		daddr;		/* header location */
> +	size_t			numblks;	/* size of header */
> +	xfs_btnum_t		type;		/* type of btree root block */
> +	int			numrecs;	/* recs in btree root block */
> +};
> +
> +int xfs_ag_init_headers( struct xfs_mount *mp, struct aghdr_init_data *id);
> +
> +#endif /* __LIBXFS_AG_H */
> diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
> index d9b94bd5f689..75b2fee6f99a 100644
> --- a/fs/xfs/libxfs/xfs_sb.c
> +++ b/fs/xfs/libxfs/xfs_sb.c
> @@ -888,6 +888,79 @@ xfs_sync_sb(
>  	return xfs_trans_commit(tp);
>  }
>  
> +/*
> + * Update all the secondary superblocks to match the new state of the primary.
> + * Because we are completely overwriting all the existing fields in the
> + * secondary superblock buffers, there is no need to read them in from disk.
> + * Just get a new buffer, stamp it and write it.
> + *
> + * The sb buffers need to be cached here so that we serialise against other
> + * operations that access the secondary superblocks, but we don't want to keep
> + * them in memory once it is written so we mark it as a one-shot buffer.
> + */
> +int
> +xfs_update_secondary_sbs(
> +	struct xfs_mount	*mp)
> +{
> +	xfs_agnumber_t		agno;
> +	int			saved_error = 0;
> +	int			error = 0;
> +	LIST_HEAD		(buffer_list);
> +
> +	/* update secondary superblocks. */
> +	for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
> +		struct xfs_buf		*bp;
> +
> +		bp = xfs_buf_get(mp->m_ddev_targp,
> +				 XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
> +				 XFS_FSS_TO_BB(mp, 1), 0);
> +		/*
> +		 * If we get an error reading or writing alternate superblocks,
> +		 * continue.  xfs_repair chooses the "best" superblock based
> +		 * on most matches; if we break early, we'll leave more
> +		 * superblocks un-updated than updated, and xfs_repair may
> +		 * pick them over the properly-updated primary.
> +		 */
> +		if (!bp) {
> +			xfs_warn(mp,
> +		"error allocating secondary superblock for ag %d",
> +				agno);
> +			if (!saved_error)
> +				saved_error = -ENOMEM;
> +			continue;
> +		}
> +
> +		bp->b_ops = &xfs_sb_buf_ops;
> +		xfs_buf_oneshot(bp);
> +		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
> +		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
> +		xfs_buf_delwri_queue(bp, &buffer_list);
> +		xfs_buf_relse(bp);
> +
> +		/* don't hold too many buffers at once */
> +		if (agno % 16)
> +			continue;
> +
> +		error = xfs_buf_delwri_submit(&buffer_list);
> +		if (error) {
> +			xfs_warn(mp,
> +		"write error %d updating a secondary superblock near ag %d",
> +				error, agno);
> +			if (!saved_error)
> +				saved_error = error;
> +			continue;
> +		}
> +	}
> +	error = xfs_buf_delwri_submit(&buffer_list);
> +	if (error) {
> +		xfs_warn(mp,
> +		"write error %d updating a secondary superblock near ag %d",
> +			error, agno);
> +	}
> +
> +	return saved_error ? saved_error : error;
> +}
> +
>  int
>  xfs_fs_geometry(
>  	struct xfs_sb		*sbp,
> diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
> index 63dcd2a1a657..bb0196b56fa5 100644
> --- a/fs/xfs/libxfs/xfs_sb.h
> +++ b/fs/xfs/libxfs/xfs_sb.h
> @@ -18,6 +18,13 @@
>  #ifndef __XFS_SB_H__
>  #define	__XFS_SB_H__
>  
> +struct xfs_mount;
> +struct xfs_sb;
> +struct xfs_dsb;
> +struct xfs_trans;
> +struct xfs_fsop_geom;
> +struct xfs_perag;
> +
>  /*
>   * perag get/put wrappers for ref counting
>   */
> @@ -34,6 +41,8 @@ extern void	xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
>  extern void	xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
>  extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
>  
> +extern int	xfs_update_secondary_sbs(struct xfs_mount *mp);
> +
>  #define XFS_FS_GEOM_MAX_STRUCT_VER	(4)
>  extern int	xfs_fs_geometry(struct xfs_sb *sbp, struct xfs_fsop_geom *geo,
>  				int struct_version);
> diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
> index 28692b0e61ce..c5087b79bcea 100644
> --- a/fs/xfs/xfs_fsops.c
> +++ b/fs/xfs/xfs_fsops.c
> @@ -24,11 +24,7 @@
>  #include "xfs_sb.h"
>  #include "xfs_mount.h"
>  #include "xfs_defer.h"
> -#include "xfs_da_format.h"
> -#include "xfs_da_btree.h"
> -#include "xfs_inode.h"
>  #include "xfs_trans.h"
> -#include "xfs_inode_item.h"
>  #include "xfs_error.h"
>  #include "xfs_btree.h"
>  #include "xfs_alloc_btree.h"
> @@ -36,384 +32,17 @@
>  #include "xfs_rmap_btree.h"
>  #include "xfs_ialloc.h"
>  #include "xfs_fsops.h"
> -#include "xfs_itable.h"
>  #include "xfs_trans_space.h"
>  #include "xfs_rtalloc.h"
>  #include "xfs_trace.h"
>  #include "xfs_log.h"
> -#include "xfs_filestream.h"
>  #include "xfs_rmap.h"
> +#include "xfs_ag.h"
>  #include "xfs_ag_resv.h"
>  
>  /*
> - * File system operations
> - */
> -
> -static struct xfs_buf *
> -xfs_growfs_get_hdr_buf(
> -	struct xfs_mount	*mp,
> -	xfs_daddr_t		blkno,
> -	size_t			numblks,
> -	int			flags,
> -	const struct xfs_buf_ops *ops)
> -{
> -	struct xfs_buf		*bp;
> -
> -	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
> -	if (!bp)
> -		return NULL;
> -
> -	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
> -	bp->b_bn = blkno;
> -	bp->b_maps[0].bm_bn = blkno;
> -	bp->b_ops = ops;
> -
> -	return bp;
> -}
> -
> -struct aghdr_init_data {
> -	/* per ag data */
> -	xfs_agblock_t		agno;
> -	xfs_extlen_t		agsize;
> -	struct list_head	buffer_list;
> -	xfs_rfsblock_t		nfree;
> -
> -	/* per header data */
> -	xfs_daddr_t		daddr;
> -	size_t			numblks;
> -	xfs_btnum_t		type;
> -	int			numrecs;
> -};
> -
> -/*
> - * Generic btree root block init function
> - */
> -static void
> -xfs_btroot_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	xfs_btree_init_block(mp, bp, id->type, 0, id->numrecs, id->agno, 0);
> -}
> -
> -/*
> - * Alloc btree root block init functions
> - */
> -static void
> -xfs_bnoroot_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_alloc_rec	*arec;
> -
> -	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0);
> -	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
> -	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
> -	arec->ar_blockcount = cpu_to_be32(id->agsize -
> -					  be32_to_cpu(arec->ar_startblock));
> -}
> -
> -static void
> -xfs_cntroot_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_alloc_rec	*arec;
> -
> -	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0);
> -	arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
> -	arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
> -	arec->ar_blockcount = cpu_to_be32(id->agsize -
> -					  be32_to_cpu(arec->ar_startblock));
> -}
> -
> -/*
> - * Reverse map root block init
> - */
> -static void
> -xfs_rmaproot_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
> -	struct xfs_rmap_rec	*rrec;
> -
> -	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0);
> -
> -	/*
> -	 * mark the AG header regions as static metadata The BNO
> -	 * btree block is the first block after the headers, so
> -	 * it's location defines the size of region the static
> -	 * metadata consumes.
> -	 *
> -	 * Note: unlike mkfs, we never have to account for log
> -	 * space when growing the data regions
> -	 */
> -	rrec = XFS_RMAP_REC_ADDR(block, 1);
> -	rrec->rm_startblock = 0;
> -	rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
> -	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
> -	rrec->rm_offset = 0;
> -
> -	/* account freespace btree root blocks */
> -	rrec = XFS_RMAP_REC_ADDR(block, 2);
> -	rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
> -	rrec->rm_blockcount = cpu_to_be32(2);
> -	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
> -	rrec->rm_offset = 0;
> -
> -	/* account inode btree root blocks */
> -	rrec = XFS_RMAP_REC_ADDR(block, 3);
> -	rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
> -	rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
> -					  XFS_IBT_BLOCK(mp));
> -	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
> -	rrec->rm_offset = 0;
> -
> -	/* account for rmap btree root */
> -	rrec = XFS_RMAP_REC_ADDR(block, 4);
> -	rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
> -	rrec->rm_blockcount = cpu_to_be32(1);
> -	rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
> -	rrec->rm_offset = 0;
> -
> -	/* account for refc btree root */
> -	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
> -		rrec = XFS_RMAP_REC_ADDR(block, 5);
> -		rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp));
> -		rrec->rm_blockcount = cpu_to_be32(1);
> -		rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
> -		rrec->rm_offset = 0;
> -		be16_add_cpu(&block->bb_numrecs, 1);
> -	}
> -}
> -
> -/*
> - * Initialise new secondary superblocks with the pre-grow geometry, but mark
> - * them as "in progress" so we know they haven't yet been activated. This will
> - * get cleared when the update with the new geometry information is done after
> - * changes to the primary are committed. This isn't strictly necessary, but we
> - * get it for free with the delayed buffer write lists and it means we can tell
> - * if a grow operation didn't complete properly after the fact.
> - */
> -static void
> -xfs_sbblock_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
> -
> -	xfs_sb_to_disk(dsb, &mp->m_sb);
> -	dsb->sb_inprogress = 1;
> -}
> -
> -static void
> -xfs_agfblock_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_agf		*agf = XFS_BUF_TO_AGF(bp);
> -	xfs_extlen_t		tmpsize;
> -
> -	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
> -	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
> -	agf->agf_seqno = cpu_to_be32(id->agno);
> -	agf->agf_length = cpu_to_be32(id->agsize);
> -	agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
> -	agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
> -	agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
> -	agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
> -	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
> -		agf->agf_roots[XFS_BTNUM_RMAPi] =
> -					cpu_to_be32(XFS_RMAP_BLOCK(mp));
> -		agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
> -		agf->agf_rmap_blocks = cpu_to_be32(1);
> -	}
> -
> -	agf->agf_flfirst = cpu_to_be32(1);
> -	agf->agf_fllast = 0;
> -	agf->agf_flcount = 0;
> -	tmpsize = id->agsize - mp->m_ag_prealloc_blocks;
> -	agf->agf_freeblks = cpu_to_be32(tmpsize);
> -	agf->agf_longest = cpu_to_be32(tmpsize);
> -	if (xfs_sb_version_hascrc(&mp->m_sb))
> -		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
> -	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
> -		agf->agf_refcount_root = cpu_to_be32(
> -				xfs_refc_block(mp));
> -		agf->agf_refcount_level = cpu_to_be32(1);
> -		agf->agf_refcount_blocks = cpu_to_be32(1);
> -	}
> -}
> -
> -static void
> -xfs_agflblock_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_agfl		*agfl = XFS_BUF_TO_AGFL(bp);
> -	__be32			*agfl_bno;
> -	int			bucket;
> -
> -	if (xfs_sb_version_hascrc(&mp->m_sb)) {
> -		agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
> -		agfl->agfl_seqno = cpu_to_be32(id->agno);
> -		uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
> -	}
> -
> -	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
> -	for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
> -		agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
> -}
> -
> -static void
> -xfs_agiblock_init(
> -	struct xfs_mount	*mp,
> -	struct xfs_buf		*bp,
> -	struct aghdr_init_data	*id)
> -{
> -	struct xfs_agi		*agi = XFS_BUF_TO_AGI(bp);
> -	int			bucket;
> -
> -	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
> -	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
> -	agi->agi_seqno = cpu_to_be32(id->agno);
> -	agi->agi_length = cpu_to_be32(id->agsize);
> -	agi->agi_count = 0;
> -	agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
> -	agi->agi_level = cpu_to_be32(1);
> -	agi->agi_freecount = 0;
> -	agi->agi_newino = cpu_to_be32(NULLAGINO);
> -	agi->agi_dirino = cpu_to_be32(NULLAGINO);
> -	if (xfs_sb_version_hascrc(&mp->m_sb))
> -		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
> -	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
> -		agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
> -		agi->agi_free_level = cpu_to_be32(1);
> -	}
> -	for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
> -		agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
> -}
> -
> -typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,
> -				  struct aghdr_init_data *id);
> -static int
> -xfs_growfs_init_aghdr(
> -	struct xfs_mount	*mp,
> -	struct aghdr_init_data	*id,
> -	aghdr_init_work_f	work,
> -	const struct xfs_buf_ops *ops)
> -
> -{
> -	struct xfs_buf		*bp;
> -
> -	bp = xfs_growfs_get_hdr_buf(mp, id->daddr, id->numblks, 0, ops);
> -	if (!bp)
> -		return -ENOMEM;
> -
> -	(*work)(mp, bp, id);
> -
> -	xfs_buf_delwri_queue(bp, &id->buffer_list);
> -	xfs_buf_relse(bp);
> -	return 0;
> -}
> -
> -struct xfs_aghdr_grow_data {
> -	xfs_daddr_t		daddr;
> -	size_t			numblks;
> -	const struct xfs_buf_ops *ops;
> -	aghdr_init_work_f	work;
> -	xfs_btnum_t		type;
> -	int			numrecs;
> -	bool			need_init;
> -};
> -
> -/*
> - * Write new AG headers to disk. Non-transactional, but written
> - * synchronously so they are completed prior to the growfs transaction
> - * being logged.
> + * growfs operations
>   */
> -static int
> -xfs_grow_ag_headers(
> -	struct xfs_mount	*mp,
> -	struct aghdr_init_data	*id)
> -
> -{
> -	struct xfs_aghdr_grow_data aghdr_data[] = {
> -		/* SB */
> -		{ XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR),
> -		  XFS_FSS_TO_BB(mp, 1), &xfs_sb_buf_ops,
> -		  &xfs_sbblock_init, 0, 0, true },
> -		/* AGF */
> -		{ XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)),
> -		  XFS_FSS_TO_BB(mp, 1), &xfs_agf_buf_ops,
> -		  &xfs_agfblock_init, 0, 0, true },
> -		/* AGFL */
> -		{ XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)),
> -		  XFS_FSS_TO_BB(mp, 1), &xfs_agfl_buf_ops,
> -		  &xfs_agflblock_init, 0, 0, true },
> -		/* AGI */
> -		{ XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)),
> -		  XFS_FSS_TO_BB(mp, 1), &xfs_agi_buf_ops,
> -		  &xfs_agiblock_init, 0, 0, true },
> -		/* BNO root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_allocbt_buf_ops,
> -		  &xfs_bnoroot_init, 0, 0, true },
> -		/* CNT root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_allocbt_buf_ops,
> -		  &xfs_cntroot_init, 0, 0, true },
> -		/* INO root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_inobt_buf_ops,
> -		  &xfs_btroot_init, XFS_BTNUM_INO, 0, true },
> -		/* FINO root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_inobt_buf_ops,
> -		  &xfs_btroot_init, XFS_BTNUM_FINO, 0,
> -		  xfs_sb_version_hasfinobt(&mp->m_sb) },
> -		/* RMAP root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_rmapbt_buf_ops,
> -		  &xfs_rmaproot_init, 0, 0,
> -		  xfs_sb_version_hasrmapbt(&mp->m_sb) },
> -		/* REFC root block */
> -		{ XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)),
> -		  BTOBB(mp->m_sb.sb_blocksize), &xfs_refcountbt_buf_ops,
> -		  &xfs_btroot_init, XFS_BTNUM_REFC, 0,
> -		  xfs_sb_version_hasreflink(&mp->m_sb) },
> -		/* NULL terminating block */
> -		{ XFS_BUF_DADDR_NULL, 0, NULL, NULL, 0, 0, false },
> -	};
> -	struct  xfs_aghdr_grow_data *dp;
> -	int			error = 0;
> -
> -	/* Account for AG free space in new AG */
> -	id->nfree += id->agsize - mp->m_ag_prealloc_blocks;
> -
> -	for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) {
> -		if (!dp->need_init)
> -			continue;
> -
> -		id->daddr = dp->daddr;
> -		id->numblks = dp->numblks;
> -		id->numrecs = dp->numrecs;
> -		id->type = dp->type;
> -		error = xfs_growfs_init_aghdr(mp, id, dp->work, dp->ops);
> -		if (error)
> -			break;
> -	}
> -	return error;
> -}
> -
>  static int
>  xfs_growfs_data_private(
>  	xfs_mount_t		*mp,		/* mount point for filesystem */
> @@ -491,7 +120,7 @@ xfs_growfs_data_private(
>  		else
>  			id.agsize = mp->m_sb.sb_agblocks;
>  
> -		error = xfs_grow_ag_headers(mp, &id);
> +		error = xfs_ag_init_headers(mp, &id);
>  		if (error) {
>  			xfs_buf_delwri_cancel(&id.buffer_list);
>  			goto out_trans_cancel;
> @@ -655,79 +284,6 @@ xfs_growfs_imaxpct(
>  	return xfs_trans_commit(tp);
>  }
>  
> -/*
> - * After a grow operation, we need to update all the secondary superblocks
> - * to match the new state of the primary. Because we are completely overwriting
> - * all the existing fields in the secondary superblock buffers, there is no need
> - * to read them in from disk. Just get a new buffer, stamp it and write it.
> - *
> - * The sb buffers need to be cached here so that we serialise against scrub
> - * scanning secondary superblocks, but we don't want to keep it in memory once
> - * it is written so we mark it as a one-shot buffer.
> - */
> -static int
> -xfs_growfs_update_superblocks(
> -	struct xfs_mount	*mp)
> -{
> -	xfs_agnumber_t		agno;
> -	int			saved_error = 0;
> -	int			error = 0;
> -	LIST_HEAD		(buffer_list);
> -
> -	/* update secondary superblocks. */
> -	for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
> -		struct xfs_buf		*bp;
> -
> -		bp = xfs_buf_get(mp->m_ddev_targp,
> -				 XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
> -				 XFS_FSS_TO_BB(mp, 1), 0);
> -		/*
> -		 * If we get an error reading or writing alternate superblocks,
> -		 * continue.  xfs_repair chooses the "best" superblock based
> -		 * on most matches; if we break early, we'll leave more
> -		 * superblocks un-updated than updated, and xfs_repair may
> -		 * pick them over the properly-updated primary.
> -		 */
> -		if (!bp) {
> -			xfs_warn(mp,
> -		"error allocating secondary superblock for ag %d",
> -				agno);
> -			if (!saved_error)
> -				saved_error = -ENOMEM;
> -			continue;
> -		}
> -
> -		bp->b_ops = &xfs_sb_buf_ops;
> -		xfs_buf_oneshot(bp);
> -		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
> -		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
> -		xfs_buf_delwri_queue(bp, &buffer_list);
> -		xfs_buf_relse(bp);
> -
> -		/* don't hold too many buffers at once */
> -		if (agno % 16)
> -			continue;
> -
> -		error = xfs_buf_delwri_submit(&buffer_list);
> -		if (error) {
> -			xfs_warn(mp,
> -		"write error %d updating a secondary superblock near ag %d",
> -				error, agno);
> -			if (!saved_error)
> -				saved_error = error;
> -			continue;
> -		}
> -	}
> -	error = xfs_buf_delwri_submit(&buffer_list);
> -	if (error) {
> -		xfs_warn(mp,
> -		"write error %d updating a secondary superblock near ag %d",
> -			error, agno);
> -	}
> -
> -	return saved_error ? saved_error : error;
> -}
> -
>  /*
>   * protected versions of growfs function acquire and release locks on the mount
>   * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
> @@ -767,7 +323,7 @@ xfs_growfs_data(
>  		mp->m_maxicount = 0;
>  
>  	/* Update secondary superblocks now the physical grow has completed */
> -	error = xfs_growfs_update_superblocks(mp);
> +	error = xfs_update_secondary_sbs(mp);
>  
>  out_error:
>  	/*
> -- 
> 2.17.0
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html