Commit 340785cc authored by Darrick J. Wong's avatar Darrick J. Wong Committed by Dave Chinner

xfs: add owner field to extent allocation and freeing

For the rmap btree to work, we have to feed the extent owner
information to the the allocation and freeing functions. This
information is what will end up in the rmap btree that tracks
allocated extents. While we technically don't need the owner
information when freeing extents, passing it allows us to validate
that the extent we are removing from the rmap btree actually
belonged to the owner we expected it to belong to.

We also define a special set of owner values for internal metadata
that would otherwise have no owner. This allows us to tell the
difference between metadata owned by different per-ag btrees, as
well as static fs metadata (e.g. AG headers) and internal journal
blocks.

There are also a couple of special cases we need to take care of -
during EFI recovery, we don't actually know who the original owner
was, so we need to pass a wildcard to indicate that we aren't
checking the owner for validity. We also need special handling in
growfs, as we "free" the space in the last AG when extending it, but
because it's new space it has no actual owner...

While touching the xfs_bmap_add_free() function, re-order the
parameters to put the struct xfs_mount first.

Extend the owner field to include both the owner type and some sort
of index within the owner.  The index field will be used to support
reverse mappings when reflink is enabled.

When we're freeing extents from an EFI, we don't have the owner
information available (rmap updates have their own redo items).
xfs_free_extent therefore doesn't need to do an rmap update. Make
sure that the log replay code signals this correctly.

This is based upon a patch originally from Dave Chinner. It has been
extended to add more owner information with the intent of helping
recovery operations when things go wrong (e.g. offset of user data
block in a file).

[dchinner: de-shout the xfs_rmap_*_owner helpers]
[darrick: minor style fixes suggested by Christoph Hellwig]
Signed-off-by: default avatarDave Chinner <dchinner@redhat.com>
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: default avatarDave Chinner <dchinner@redhat.com>
Signed-off-by: default avatarDave Chinner <david@fromorbit.com>
parent 8018026e
......@@ -36,6 +36,7 @@
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
struct workqueue_struct *xfs_alloc_wq;
......@@ -1589,14 +1590,15 @@ xfs_alloc_ag_vextent_small(
/*
* Free the extent starting at agno/bno for length.
*/
STATIC int /* error */
STATIC int
xfs_free_ag_extent(
xfs_trans_t *tp, /* transaction pointer */
xfs_buf_t *agbp, /* buffer for a.g. freelist header */
xfs_agnumber_t agno, /* allocation group number */
xfs_agblock_t bno, /* starting block number */
xfs_extlen_t len, /* length of extent */
int isfl) /* set if is freelist blocks - no sb acctg */
xfs_trans_t *tp,
xfs_buf_t *agbp,
xfs_agnumber_t agno,
xfs_agblock_t bno,
xfs_extlen_t len,
struct xfs_owner_info *oinfo,
int isfl)
{
xfs_btree_cur_t *bno_cur; /* cursor for by-block btree */
xfs_btree_cur_t *cnt_cur; /* cursor for by-size btree */
......@@ -2005,13 +2007,15 @@ xfs_alloc_fix_freelist(
* back on the free list? Maybe we should only do this when space is
* getting low or the AGFL is more than half full?
*/
xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);
while (pag->pagf_flcount > need) {
struct xfs_buf *bp;
error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);
if (error)
goto out_agbp_relse;
error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1, 1);
error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1,
&targs.oinfo, 1);
if (error)
goto out_agbp_relse;
bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
......@@ -2021,6 +2025,7 @@ xfs_alloc_fix_freelist(
memset(&targs, 0, sizeof(targs));
targs.tp = tp;
targs.mp = mp;
xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);
targs.agbp = agbp;
targs.agno = args->agno;
targs.alignment = targs.minlen = targs.prod = targs.isfl = 1;
......@@ -2709,7 +2714,8 @@ int /* error */
xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
xfs_extlen_t len) /* length of extent */
xfs_extlen_t len, /* length of extent */
struct xfs_owner_info *oinfo) /* extent owner */
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *agbp;
......@@ -2737,7 +2743,7 @@ xfs_free_extent(
agbno + len <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_length),
err);
error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, 0);
error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, oinfo, 0);
if (error)
goto err;
......
......@@ -123,6 +123,7 @@ typedef struct xfs_alloc_arg {
char isfl; /* set if is freelist blocks - !acctg */
char userdata; /* mask defining userdata treatment */
xfs_fsblock_t firstblock; /* io first block allocated */
struct xfs_owner_info oinfo; /* owner of blocks being allocated */
} xfs_alloc_arg_t;
/*
......@@ -210,7 +211,8 @@ int /* error */
xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
xfs_extlen_t len); /* length of extent */
xfs_extlen_t len, /* length of extent */
struct xfs_owner_info *oinfo);/* extent owner */
int /* error */
xfs_alloc_lookup_ge(
......
......@@ -46,6 +46,7 @@
#include "xfs_symlink.h"
#include "xfs_attr_leaf.h"
#include "xfs_filestream.h"
#include "xfs_rmap.h"
kmem_zone_t *xfs_bmap_free_item_zone;
......@@ -571,10 +572,11 @@ xfs_bmap_validate_ret(
*/
void
xfs_bmap_add_free(
struct xfs_mount *mp, /* mount point structure */
struct xfs_defer_ops *dfops, /* list of extents */
xfs_fsblock_t bno, /* fs block number of extent */
xfs_filblks_t len) /* length of extent */
struct xfs_mount *mp,
struct xfs_defer_ops *dfops,
xfs_fsblock_t bno,
xfs_filblks_t len,
struct xfs_owner_info *oinfo)
{
struct xfs_extent_free_item *new; /* new element */
#ifdef DEBUG
......@@ -593,9 +595,14 @@ xfs_bmap_add_free(
ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
#endif
ASSERT(xfs_bmap_free_item_zone != NULL);
new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
new->xefi_startblock = bno;
new->xefi_blockcount = (xfs_extlen_t)len;
if (oinfo)
new->xefi_oinfo = *oinfo;
else
xfs_rmap_skip_owner_update(&new->xefi_oinfo);
trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
XFS_FSB_TO_AGBNO(mp, bno), len);
xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
......@@ -628,6 +635,7 @@ xfs_bmap_btree_to_extents(
xfs_mount_t *mp; /* mount point structure */
__be64 *pp; /* ptr to block address */
struct xfs_btree_block *rblock;/* root btree block */
struct xfs_owner_info oinfo;
mp = ip->i_mount;
ifp = XFS_IFORK_PTR(ip, whichfork);
......@@ -651,7 +659,8 @@ xfs_bmap_btree_to_extents(
cblock = XFS_BUF_TO_BLOCK(cbp);
if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
return error;
xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1);
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo);
ip->i_d.di_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
......@@ -732,6 +741,7 @@ xfs_bmap_extents_to_btree(
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = mp;
xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
args.firstblock = *firstblock;
if (*firstblock == NULLFSBLOCK) {
args.type = XFS_ALLOCTYPE_START_BNO;
......@@ -878,6 +888,7 @@ xfs_bmap_local_to_extents(
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = ip->i_mount;
xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
args.firstblock = *firstblock;
/*
* Allocate a block. We know we need only one, since the
......@@ -3660,6 +3671,7 @@ xfs_bmap_btalloc(
args.tp = ap->tp;
args.mp = mp;
args.fsbno = ap->blkno;
xfs_rmap_skip_owner_update(&args.oinfo);
/* Trim the allocation back to the maximum an AG can fit. */
args.maxlen = MIN(ap->length, XFS_ALLOC_AG_MAX_USABLE(mp));
......@@ -4839,6 +4851,7 @@ xfs_bmap_del_extent(
nblks = 0;
do_fx = 0;
}
/*
* Set flag value to use in switch statement.
* Left-contig is 2, right-contig is 1.
......@@ -5026,7 +5039,7 @@ xfs_bmap_del_extent(
*/
if (do_fx)
xfs_bmap_add_free(mp, dfops, del->br_startblock,
del->br_blockcount);
del->br_blockcount, NULL);
/*
* Adjust inode # blocks in the file.
*/
......
......@@ -67,6 +67,7 @@ struct xfs_extent_free_item
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct list_head xefi_list;
struct xfs_owner_info xefi_oinfo; /* extent owner */
};
#define XFS_BMAP_MAX_NMAP 4
......@@ -165,7 +166,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
xfs_fsblock_t bno, xfs_filblks_t len);
xfs_fsblock_t bno, xfs_filblks_t len,
struct xfs_owner_info *oinfo);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
......
......@@ -35,6 +35,7 @@
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_rmap.h"
/*
* Determine the extent state.
......@@ -447,6 +448,8 @@ xfs_bmbt_alloc_block(
args.mp = cur->bc_mp;
args.fsbno = cur->bc_private.b.firstblock;
args.firstblock = args.fsbno;
xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
cur->bc_private.b.whichfork);
if (args.fsbno == NULLFSBLOCK) {
args.fsbno = be64_to_cpu(start->l);
......@@ -526,8 +529,10 @@ xfs_bmbt_free_block(
struct xfs_inode *ip = cur->bc_private.b.ip;
struct xfs_trans *tp = cur->bc_tp;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
struct xfs_owner_info oinfo;
xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1);
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);
ip->i_d.di_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
......
......@@ -1319,6 +1319,34 @@ typedef __be32 xfs_inobt_ptr_t;
*/
#define XFS_RMAP_CRC_MAGIC 0x524d4233 /* 'RMB3' */
/*
* Ownership info for an extent. This is used to create reverse-mapping
* entries.
*/
#define XFS_OWNER_INFO_ATTR_FORK (1 << 0)
#define XFS_OWNER_INFO_BMBT_BLOCK (1 << 1)
struct xfs_owner_info {
uint64_t oi_owner;
xfs_fileoff_t oi_offset;
unsigned int oi_flags;
};
/*
* Special owner types.
*
* Seeing as we only support up to 8EB, we have the upper bit of the owner field
* to tell us we have a special owner value. We use these for static metadata
* allocated at mkfs/growfs time, as well as for freespace management metadata.
*/
#define XFS_RMAP_OWN_NULL (-1ULL) /* No owner, for growfs */
#define XFS_RMAP_OWN_UNKNOWN (-2ULL) /* Unknown owner, for EFI recovery */
#define XFS_RMAP_OWN_FS (-3ULL) /* static fs metadata */
#define XFS_RMAP_OWN_LOG (-4ULL) /* static fs metadata */
#define XFS_RMAP_OWN_AG (-5ULL) /* AG freespace btree blocks */
#define XFS_RMAP_OWN_INOBT (-6ULL) /* Inode btree blocks */
#define XFS_RMAP_OWN_INODES (-7ULL) /* Inode chunk */
#define XFS_RMAP_OWN_MIN (-8ULL) /* guard */
#define XFS_RMAP_BLOCK(mp) \
(xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
XFS_FIBT_BLOCK(mp) + 1 : \
......
......@@ -40,6 +40,7 @@
#include "xfs_icache.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
/*
......@@ -615,6 +616,7 @@ xfs_ialloc_ag_alloc(
args.tp = tp;
args.mp = tp->t_mountp;
args.fsbno = NULLFSBLOCK;
xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_INODES);
#ifdef DEBUG
/* randomly do sparse inode allocations */
......@@ -1825,12 +1827,14 @@ xfs_difree_inode_chunk(
int nextbit;
xfs_agblock_t agbno;
int contigblk;
struct xfs_owner_info oinfo;
DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);
xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
if (!xfs_inobt_issparse(rec->ir_holemask)) {
/* not sparse, calculate extent info directly */
xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, sagbno),
mp->m_ialloc_blks);
mp->m_ialloc_blks, &oinfo);
return;
}
......@@ -1874,7 +1878,7 @@ xfs_difree_inode_chunk(
ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, agbno),
contigblk);
contigblk, &oinfo);
/* reset range to current bit and carry on... */
startidx = endidx = nextbit;
......
......@@ -32,6 +32,7 @@
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_trans.h"
#include "xfs_rmap.h"
STATIC int
......@@ -96,6 +97,7 @@ xfs_inobt_alloc_block(
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_INOBT);
args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno, sbno);
args.minlen = 1;
args.maxlen = 1;
......@@ -125,8 +127,12 @@ xfs_inobt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
struct xfs_owner_info oinfo;
xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
return xfs_free_extent(cur->bc_tp,
XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1);
XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1,
&oinfo);
}
STATIC int
......
/*
* Copyright (C) 2016 Oracle. All Rights Reserved.
*
* Author: Darrick J. Wong <darrick.wong@oracle.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
*/
#ifndef __XFS_RMAP_H__
#define __XFS_RMAP_H__
static inline void
xfs_rmap_ag_owner(
struct xfs_owner_info *oi,
uint64_t owner)
{
oi->oi_owner = owner;
oi->oi_offset = 0;
oi->oi_flags = 0;
}
static inline void
xfs_rmap_ino_bmbt_owner(
struct xfs_owner_info *oi,
xfs_ino_t ino,
int whichfork)
{
oi->oi_owner = ino;
oi->oi_offset = 0;
oi->oi_flags = XFS_OWNER_INFO_BMBT_BLOCK;
if (whichfork == XFS_ATTR_FORK)
oi->oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
}
static inline void
xfs_rmap_ino_owner(
struct xfs_owner_info *oi,
xfs_ino_t ino,
int whichfork,
xfs_fileoff_t offset)
{
oi->oi_owner = ino;
oi->oi_offset = offset;
oi->oi_flags = 0;
if (whichfork == XFS_ATTR_FORK)
oi->oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
}
static inline void
xfs_rmap_skip_owner_update(
struct xfs_owner_info *oi)
{
oi->oi_owner = XFS_RMAP_OWN_UNKNOWN;
}
#endif /* __XFS_RMAP_H__ */
......@@ -27,6 +27,8 @@
#include "xfs_buf_item.h"
#include "xfs_extfree_item.h"
#include "xfs_log.h"
#include "xfs_btree.h"
#include "xfs_rmap.h"
kmem_zone_t *xfs_efi_zone;
......@@ -503,6 +505,7 @@ xfs_efi_recover(
int error = 0;
xfs_extent_t *extp;
xfs_fsblock_t startblock_fsb;
struct xfs_owner_info oinfo;
ASSERT(!test_bit(XFS_EFI_RECOVERED, &efip->efi_flags));
......@@ -534,10 +537,11 @@ xfs_efi_recover(
return error;
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
xfs_rmap_skip_owner_update(&oinfo);
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
extp = &(efip->efi_format.efi_extents[i]);
error = xfs_trans_free_extent(tp, efdp, extp->ext_start,
extp->ext_len);
extp->ext_len, &oinfo);
if (error)
goto abort_error;
......
......@@ -41,6 +41,7 @@
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_filestream.h"
#include "xfs_rmap.h"
/*
* File system operations
......@@ -436,6 +437,8 @@ xfs_growfs_data_private(
* There are new blocks in the old last a.g.
*/
if (new) {
struct xfs_owner_info oinfo;
/*
* Change the agi length.
*/
......@@ -463,15 +466,21 @@ xfs_growfs_data_private(
be32_to_cpu(agi->agi_length));
xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
/*
* Free the new space.
*
* XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
* this doesn't actually exist in the rmap btree.
*/
error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno,
be32_to_cpu(agf->agf_length) - new), new);
if (error) {
xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
error = xfs_free_extent(tp,
XFS_AGB_TO_FSB(mp, agno,
be32_to_cpu(agf->agf_length) - new),
new, &oinfo);
if (error)
goto error0;
}
}
/*
* Update changed superblock fields transactionally. These are not
......
......@@ -217,7 +217,7 @@ struct xfs_efd_log_item *xfs_trans_get_efd(struct xfs_trans *,
uint);
int xfs_trans_free_extent(struct xfs_trans *,
struct xfs_efd_log_item *, xfs_fsblock_t,
xfs_extlen_t);
xfs_extlen_t, struct xfs_owner_info *);
int xfs_trans_commit(struct xfs_trans *);
int __xfs_trans_roll(struct xfs_trans **, struct xfs_inode *, int *);
int xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
......
......@@ -120,13 +120,14 @@ xfs_trans_free_extent(
struct xfs_trans *tp,
struct xfs_efd_log_item *efdp,
xfs_fsblock_t start_block,
xfs_extlen_t ext_len)
xfs_extlen_t ext_len,
struct xfs_owner_info *oinfo)
{
uint next_extent;
struct xfs_extent *extp;
int error;
error = xfs_free_extent(tp, start_block, ext_len);
error = xfs_free_extent(tp, start_block, ext_len, oinfo);
/*
* Mark the transaction dirty, even on error. This ensures the
......@@ -213,7 +214,8 @@ xfs_extent_free_finish_item(
free = container_of(item, struct xfs_extent_free_item, xefi_list);
error = xfs_trans_free_extent(tp, done_item,
free->xefi_startblock,
free->xefi_blockcount);
free->xefi_blockcount,
&free->xefi_oinfo);
kmem_free(free);
return error;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment