hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
linux-sg2042/fs/xfs/libxfs/xfs_refcount_btree.c

444 lines
10 KiB
C
Raw Normal View History

xfs: convert to SPDX license tags Remove the verbose license text from XFS files and replace them with SPDX tags. This does not change the license of any of the code, merely refers to the common, up-to-date license files in LICENSES/ This change was mostly scripted. fs/xfs/Makefile and fs/xfs/libxfs/xfs_fs.h were modified by hand, the rest were detected and modified by the following command: for f in `git grep -l "GNU General" fs/xfs/` ; do echo $f cat $f | awk -f hdr.awk > $f.new mv -f $f.new $f done And the hdr.awk script that did the modification (including detecting the difference between GPL-2.0 and GPL-2.0+ licenses) is as follows: $ cat hdr.awk BEGIN { hdr = 1.0 tag = "GPL-2.0" str = "" } /^ \* This program is free software/ { hdr = 2.0; next } /any later version./ { tag = "GPL-2.0+" next } /^ \*\// { if (hdr > 0.0) { print "// SPDX-License-Identifier: " tag print str print $0 str="" hdr = 0.0 next } print $0 next } /^ \* / { if (hdr > 1.0) next if (hdr > 0.0) { if (str != "") str = str "\n" str = str $0 next } print $0 next } /^ \*/ { if (hdr > 0.0) next print $0 next } // { if (hdr > 0.0) { if (str != "") str = str "\n" str = str $0 next } print $0 } END { } $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-06-06 10:42:14 +08:00
// SPDX-License-Identifier: GPL-2.0+
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
/*
* 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_sb.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_refcount_btree.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_trans.h"
#include "xfs_bit.h"
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
#include "xfs_rmap.h"
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
static struct xfs_btree_cur *
xfs_refcountbt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
xfs: remove unused btree cursor bc_private.a.dfops field The xfs_btree_cur.bc_private.a.dfops field is only ever initialized by the refcountbt cursor init function. The only caller of that function with a non-NULL dfops is from deferred completion context, which already has attached to ->t_dfops. In addition to that, the only actual reference of a.dfops is the cursor duplication function, which means the field is effectively unused. Remove the dfops field from the bc_private.a union. Any future users can acquire the dfops from the transaction. This patch does not change behavior. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-07-12 13:26:17 +08:00
cur->bc_private.a.agbp, cur->bc_private.a.agno);
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
}
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
STATIC void
xfs_refcountbt_set_root(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr,
int inc)
{
struct xfs_buf *agbp = cur->bc_private.a.agbp;
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
xfs_agnumber_t seqno = be32_to_cpu(agf->agf_seqno);
struct xfs_perag *pag = xfs_perag_get(cur->bc_mp, seqno);
ASSERT(ptr->s != 0);
agf->agf_refcount_root = ptr->s;
be32_add_cpu(&agf->agf_refcount_level, inc);
pag->pagf_refcount_level += inc;
xfs_perag_put(pag);
xfs_alloc_log_agf(cur->bc_tp, agbp,
XFS_AGF_REFCOUNT_ROOT | XFS_AGF_REFCOUNT_LEVEL);
}
STATIC int
xfs_refcountbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
int *stat)
{
struct xfs_buf *agbp = cur->bc_private.a.agbp;
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
struct xfs_alloc_arg args; /* block allocation args */
int error; /* error return value */
memset(&args, 0, sizeof(args));
args.tp = cur->bc_tp;
args.mp = cur->bc_mp;
args.type = XFS_ALLOCTYPE_NEAR_BNO;
args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
xfs_refc_block(args.mp));
xfs: remove xfs_rmap_ag_owner and friends Owner information for static fs metadata can be defined readonly at build time because it never changes across filesystems. This enables us to reduce stack usage (particularly in scrub) because we can use the statically defined oinfo structures. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
2018-12-13 00:46:23 +08:00
args.oinfo = XFS_RMAP_OINFO_REFC;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
args.minlen = args.maxlen = args.prod = 1;
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
args.resv = XFS_AG_RESV_METADATA;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
error = xfs_alloc_vextent(&args);
if (error)
goto out_error;
trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_private.a.agno,
args.agbno, 1);
if (args.fsbno == NULLFSBLOCK) {
*stat = 0;
return 0;
}
ASSERT(args.agno == cur->bc_private.a.agno);
ASSERT(args.len == 1);
new->s = cpu_to_be32(args.agbno);
be32_add_cpu(&agf->agf_refcount_blocks, 1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
*stat = 1;
return 0;
out_error:
return error;
}
STATIC int
xfs_refcountbt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
struct xfs_mount *mp = cur->bc_mp;
struct xfs_buf *agbp = cur->bc_private.a.agbp;
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
int error;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_private.a.agno,
XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
be32_add_cpu(&agf->agf_refcount_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
xfs: remove xfs_rmap_ag_owner and friends Owner information for static fs metadata can be defined readonly at build time because it never changes across filesystems. This enables us to reduce stack usage (particularly in scrub) because we can use the statically defined oinfo structures. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
2018-12-13 00:46:23 +08:00
error = xfs_free_extent(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC,
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
XFS_AG_RESV_METADATA);
if (error)
return error;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
return error;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
}
STATIC int
xfs_refcountbt_get_minrecs(
struct xfs_btree_cur *cur,
int level)
{
return cur->bc_mp->m_refc_mnr[level != 0];
}
STATIC int
xfs_refcountbt_get_maxrecs(
struct xfs_btree_cur *cur,
int level)
{
return cur->bc_mp->m_refc_mxr[level != 0];
}
STATIC void
xfs_refcountbt_init_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
key->refc.rc_startblock = rec->refc.rc_startblock;
}
STATIC void
xfs_refcountbt_init_high_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
__u32 x;
x = be32_to_cpu(rec->refc.rc_startblock);
x += be32_to_cpu(rec->refc.rc_blockcount) - 1;
key->refc.rc_startblock = cpu_to_be32(x);
}
STATIC void
xfs_refcountbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock);
rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount);
rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount);
}
STATIC void
xfs_refcountbt_init_ptr_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr)
{
struct xfs_agf *agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
ASSERT(cur->bc_private.a.agno == be32_to_cpu(agf->agf_seqno));
ptr->s = agf->agf_refcount_root;
}
xfs: remove double-underscore integer types This is a purely mechanical patch that removes the private __{u,}int{8,16,32,64}_t typedefs in favor of using the system {u,}int{8,16,32,64}_t typedefs. This is the sed script used to perform the transformation and fix the resulting whitespace and indentation errors: s/typedef\t__uint8_t/typedef __uint8_t\t/g s/typedef\t__uint/typedef __uint/g s/typedef\t__int\([0-9]*\)_t/typedef int\1_t\t/g s/__uint8_t\t/__uint8_t\t\t/g s/__uint/uint/g s/__int\([0-9]*\)_t\t/__int\1_t\t\t/g s/__int/int/g /^typedef.*int[0-9]*_t;$/d Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-06-17 02:00:05 +08:00
STATIC int64_t
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
xfs_refcountbt_key_diff(
struct xfs_btree_cur *cur,
union xfs_btree_key *key)
{
struct xfs_refcount_irec *rec = &cur->bc_rec.rc;
struct xfs_refcount_key *kp = &key->refc;
xfs: remove double-underscore integer types This is a purely mechanical patch that removes the private __{u,}int{8,16,32,64}_t typedefs in favor of using the system {u,}int{8,16,32,64}_t typedefs. This is the sed script used to perform the transformation and fix the resulting whitespace and indentation errors: s/typedef\t__uint8_t/typedef __uint8_t\t/g s/typedef\t__uint/typedef __uint/g s/typedef\t__int\([0-9]*\)_t/typedef int\1_t\t/g s/__uint8_t\t/__uint8_t\t\t/g s/__uint/uint/g s/__int\([0-9]*\)_t\t/__int\1_t\t\t/g s/__int/int/g /^typedef.*int[0-9]*_t;$/d Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-06-17 02:00:05 +08:00
return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
}
xfs: remove double-underscore integer types This is a purely mechanical patch that removes the private __{u,}int{8,16,32,64}_t typedefs in favor of using the system {u,}int{8,16,32,64}_t typedefs. This is the sed script used to perform the transformation and fix the resulting whitespace and indentation errors: s/typedef\t__uint8_t/typedef __uint8_t\t/g s/typedef\t__uint/typedef __uint/g s/typedef\t__int\([0-9]*\)_t/typedef int\1_t\t/g s/__uint8_t\t/__uint8_t\t\t/g s/__uint/uint/g s/__int\([0-9]*\)_t\t/__int\1_t\t\t/g s/__int/int/g /^typedef.*int[0-9]*_t;$/d Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-06-17 02:00:05 +08:00
STATIC int64_t
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
xfs_refcountbt_diff_two_keys(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
xfs: remove double-underscore integer types This is a purely mechanical patch that removes the private __{u,}int{8,16,32,64}_t typedefs in favor of using the system {u,}int{8,16,32,64}_t typedefs. This is the sed script used to perform the transformation and fix the resulting whitespace and indentation errors: s/typedef\t__uint8_t/typedef __uint8_t\t/g s/typedef\t__uint/typedef __uint/g s/typedef\t__int\([0-9]*\)_t/typedef int\1_t\t/g s/__uint8_t\t/__uint8_t\t\t/g s/__uint/uint/g s/__int\([0-9]*\)_t\t/__int\1_t\t\t/g s/__int/int/g /^typedef.*int[0-9]*_t;$/d Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-06-17 02:00:05 +08:00
return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
be32_to_cpu(k2->refc.rc_startblock);
}
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
STATIC xfs_failaddr_t
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
xfs_refcountbt_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
struct xfs_perag *pag = bp->b_pag;
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
xfs_failaddr_t fa;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
unsigned int level;
xfs: miscellaneous verifier magic value fixups Most buffer verifiers have hardcoded magic value checks conditionalized on the version of the filesystem. The magic value field of the verifier structure facilitates abstraction of some of this code. Populate the ->magic field of various verifiers to take advantage of this abstraction. No functional changes. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-08 02:45:48 +08:00
if (!xfs_verify_magic(bp, block->bb_magic))
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
return __this_address;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
if (!xfs_sb_version_hasreflink(&mp->m_sb))
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
return __this_address;
fa = xfs_btree_sblock_v5hdr_verify(bp);
if (fa)
return fa;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
level = be16_to_cpu(block->bb_level);
if (pag && pag->pagf_init) {
if (level >= pag->pagf_refcount_level)
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
return __this_address;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
} else if (level >= mp->m_refc_maxlevels)
xfs: have buffer verifier functions report failing address Modify each function that checks the contents of a metadata buffer to return the instruction address of the failing test so that we can report more precise failure errors to the log. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
return __this_address;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
return xfs_btree_sblock_verify(bp, mp->m_refc_mxr[level != 0]);
}
STATIC void
xfs_refcountbt_read_verify(
struct xfs_buf *bp)
{
xfs: refactor verifier callers to print address of failing check Refactor the callers of verifiers to print the instruction address of a failing check. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
xfs_failaddr_t fa;
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
if (!xfs_btree_sblock_verify_crc(bp))
xfs: refactor verifier callers to print address of failing check Refactor the callers of verifiers to print the instruction address of a failing check. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_refcountbt_verify(bp);
if (fa)
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
}
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
xfs: refactor xfs_verifier_error and xfs_buf_ioerror Since all verification errors also mark the buffer as having an error, we can combine these two calls. Later we'll add a xfs_failaddr_t parameter to promote the idea of reporting corruption errors and the address of the failing check to enable better debugging reports. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:02 +08:00
if (bp->b_error)
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
trace_xfs_btree_corrupt(bp, _RET_IP_);
}
STATIC void
xfs_refcountbt_write_verify(
struct xfs_buf *bp)
{
xfs: refactor verifier callers to print address of failing check Refactor the callers of verifiers to print the instruction address of a failing check. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
xfs_failaddr_t fa;
fa = xfs_refcountbt_verify(bp);
if (fa) {
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
trace_xfs_btree_corrupt(bp, _RET_IP_);
xfs: refactor verifier callers to print address of failing check Refactor the callers of verifiers to print the instruction address of a failing check. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:03 +08:00
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
return;
}
xfs_btree_sblock_calc_crc(bp);
}
const struct xfs_buf_ops xfs_refcountbt_buf_ops = {
.name = "xfs_refcountbt",
xfs: miscellaneous verifier magic value fixups Most buffer verifiers have hardcoded magic value checks conditionalized on the version of the filesystem. The magic value field of the verifier structure facilitates abstraction of some of this code. Populate the ->magic field of various verifiers to take advantage of this abstraction. No functional changes. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-02-08 02:45:48 +08:00
.magic = { 0, cpu_to_be32(XFS_REFC_CRC_MAGIC) },
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
.verify_read = xfs_refcountbt_read_verify,
.verify_write = xfs_refcountbt_write_verify,
xfs: create a new buf_ops pointer to verify structure metadata Expose all metadata structure buffer verifier functions via buf_ops. These will be used by the online scrub mechanism to look for problems with buffers that are already sitting around in memory. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2018-01-09 02:51:08 +08:00
.verify_struct = xfs_refcountbt_verify,
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
};
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
STATIC int
xfs_refcountbt_keys_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
return be32_to_cpu(k1->refc.rc_startblock) <
be32_to_cpu(k2->refc.rc_startblock);
}
STATIC int
xfs_refcountbt_recs_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_rec *r1,
union xfs_btree_rec *r2)
{
return be32_to_cpu(r1->refc.rc_startblock) +
be32_to_cpu(r1->refc.rc_blockcount) <=
be32_to_cpu(r2->refc.rc_startblock);
}
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
static const struct xfs_btree_ops xfs_refcountbt_ops = {
.rec_len = sizeof(struct xfs_refcount_rec),
.key_len = sizeof(struct xfs_refcount_key),
.dup_cursor = xfs_refcountbt_dup_cursor,
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
.set_root = xfs_refcountbt_set_root,
.alloc_block = xfs_refcountbt_alloc_block,
.free_block = xfs_refcountbt_free_block,
.get_minrecs = xfs_refcountbt_get_minrecs,
.get_maxrecs = xfs_refcountbt_get_maxrecs,
.init_key_from_rec = xfs_refcountbt_init_key_from_rec,
.init_high_key_from_rec = xfs_refcountbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_refcountbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_refcountbt_init_ptr_from_cur,
.key_diff = xfs_refcountbt_key_diff,
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
.buf_ops = &xfs_refcountbt_buf_ops,
xfs: add refcount btree operations Implement the generic btree operations required to manipulate refcount btree blocks. The implementation is similar to the bmapbt, though it will only allocate and free blocks from the AG. Since the refcount root and level fields are separate from the existing roots and levels array, they need a separate logging flag. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch: fix logging of AGF refcount btree fields] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:19 +08:00
.diff_two_keys = xfs_refcountbt_diff_two_keys,
.keys_inorder = xfs_refcountbt_keys_inorder,
.recs_inorder = xfs_refcountbt_recs_inorder,
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
};
/*
* Allocate a new refcount btree cursor.
*/
struct xfs_btree_cur *
xfs_refcountbt_init_cursor(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs: remove unused btree cursor bc_private.a.dfops field The xfs_btree_cur.bc_private.a.dfops field is only ever initialized by the refcountbt cursor init function. The only caller of that function with a non-NULL dfops is from deferred completion context, which already has attached to ->t_dfops. In addition to that, the only actual reference of a.dfops is the cursor duplication function, which means the field is effectively unused. Remove the dfops field from the bc_private.a union. Any future users can acquire the dfops from the transaction. This patch does not change behavior. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-07-12 13:26:17 +08:00
xfs_agnumber_t agno)
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
{
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
struct xfs_btree_cur *cur;
ASSERT(agno != NULLAGNUMBER);
ASSERT(agno < mp->m_sb.sb_agcount);
cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
cur->bc_tp = tp;
cur->bc_mp = mp;
cur->bc_btnum = XFS_BTNUM_REFC;
cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_ops = &xfs_refcountbt_ops;
xfs: make xfs btree stats less huge Embedding a switch statement in every btree stats inc/add adds a lot of code overhead to the core btree infrastructure paths. Stats are supposed to be small and lightweight, but the btree stats have become big and bloated as we've added more btrees. It needs fixing because the reflink code will just add more overhead again. Convert the v2 btree stats to arrays instead of independent variables, and instead use the type to index the specific btree array via an enum. This allows us to use array based indexing to update the stats, rather than having to derefence variables specific to the btree type. If we then wrap the xfsstats structure in a union and place uint32_t array beside it, and calculate the correct btree stats array base array index when creating a btree cursor, we can easily access entries in the stats structure without having to switch names based on the btree type. We then replace with the switch statement with a simple set of stats wrapper macros, resulting in a significant simplification of the btree stats code, and: text data bss dec hex filename 48905 144 8 49057 bfa1 fs/xfs/libxfs/xfs_btree.o.old 36793 144 8 36945 9051 fs/xfs/libxfs/xfs_btree.o it reduces the core btree infrastructure code size by close to 25%! Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-12-05 11:38:58 +08:00
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level);
cur->bc_private.a.agbp = agbp;
cur->bc_private.a.agno = agno;
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
cur->bc_private.a.priv.refc.nr_ops = 0;
cur->bc_private.a.priv.refc.shape_changes = 0;
return cur;
}
/*
* Calculate the number of records in a refcount btree block.
*/
int
xfs_refcountbt_maxrecs(
int blocklen,
bool leaf)
{
blocklen -= XFS_REFCOUNT_BLOCK_LEN;
if (leaf)
return blocklen / sizeof(struct xfs_refcount_rec);
return blocklen / (sizeof(struct xfs_refcount_key) +
sizeof(xfs_refcount_ptr_t));
}
/* Compute the maximum height of a refcount btree. */
void
xfs_refcountbt_compute_maxlevels(
struct xfs_mount *mp)
{
xfs: non-scrub - remove unused function parameters Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-04-07 01:09:42 +08:00
mp->m_refc_maxlevels = xfs_btree_compute_maxlevels(
xfs: define the on-disk refcount btree format Start constructing the refcount btree implementation by establishing the on-disk format and everything needed to read, write, and manipulate the refcount btree blocks. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:18 +08:00
mp->m_refc_mnr, mp->m_sb.sb_agblocks);
}
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
/* Calculate the refcount btree size for some records. */
xfs_extlen_t
xfs_refcountbt_calc_size(
struct xfs_mount *mp,
unsigned long long len)
{
xfs: non-scrub - remove unused function parameters Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-04-07 01:09:42 +08:00
return xfs_btree_calc_size(mp->m_refc_mnr, len);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
}
/*
* Calculate the maximum refcount btree size.
*/
xfs_extlen_t
xfs_refcountbt_max_size(
xfs: use the actual AG length when reserving blocks We need to use the actual AG length when making per-AG reservations, since we could otherwise end up reserving more blocks out of the last AG than there are actual blocks. Complained-about-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-01-04 10:39:33 +08:00
struct xfs_mount *mp,
xfs_agblock_t agblocks)
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
{
/* Bail out if we're uninitialized, which can happen in mkfs. */
if (mp->m_refc_mxr[0] == 0)
return 0;
xfs: use the actual AG length when reserving blocks We need to use the actual AG length when making per-AG reservations, since we could otherwise end up reserving more blocks out of the last AG than there are actual blocks. Complained-about-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-01-04 10:39:33 +08:00
return xfs_refcountbt_calc_size(mp, agblocks);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
}
/*
* Figure out how many blocks to reserve and how many are used by this btree.
*/
int
xfs_refcountbt_calc_reserves(
struct xfs_mount *mp,
xfs: pass transaction lock while setting up agresv on cyclic metadata Pass a tranaction pointer through to all helpers that calculate the per-AG block reservation. Online repair will use this to reinitialize per-ag reservations while it still holds all the AG headers locked to the repair transaction. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
2018-07-30 13:37:08 +08:00
struct xfs_trans *tp,
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
xfs_agnumber_t agno,
xfs_extlen_t *ask,
xfs_extlen_t *used)
{
struct xfs_buf *agbp;
struct xfs_agf *agf;
xfs: use the actual AG length when reserving blocks We need to use the actual AG length when making per-AG reservations, since we could otherwise end up reserving more blocks out of the last AG than there are actual blocks. Complained-about-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-01-04 10:39:33 +08:00
xfs_agblock_t agblocks;
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
xfs_extlen_t tree_len;
int error;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return 0;
xfs: pass transaction lock while setting up agresv on cyclic metadata Pass a tranaction pointer through to all helpers that calculate the per-AG block reservation. Online repair will use this to reinitialize per-ag reservations while it still holds all the AG headers locked to the repair transaction. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
2018-07-30 13:37:08 +08:00
error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
if (error)
return error;
agf = XFS_BUF_TO_AGF(agbp);
xfs: use the actual AG length when reserving blocks We need to use the actual AG length when making per-AG reservations, since we could otherwise end up reserving more blocks out of the last AG than there are actual blocks. Complained-about-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-01-04 10:39:33 +08:00
agblocks = be32_to_cpu(agf->agf_length);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
tree_len = be32_to_cpu(agf->agf_refcount_blocks);
xfs: pass transaction lock while setting up agresv on cyclic metadata Pass a tranaction pointer through to all helpers that calculate the per-AG block reservation. Online repair will use this to reinitialize per-ag reservations while it still holds all the AG headers locked to the repair transaction. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
2018-07-30 13:37:08 +08:00
xfs_trans_brelse(tp, agbp);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
xfs: don't reserve per-AG space for an internal log It turns out that the log can consume nearly all the space in an AG, and when this happens this it's possible that there will be less free space in the AG than the reservation would try to hide. On a debug kernel this can trigger an ASSERT in xfs/250: XFS: Assertion failed: xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved + xfs_perag_resv(pag, XFS_AG_RESV_RMAPBT)->ar_reserved <= pag->pagf_freeblks + pag->pagf_flcount, file: fs/xfs/libxfs/xfs_ag_resv.c, line: 319 The log is permanently allocated, so we know we're never going to have to expand the btrees to hold any records associated with the log space. We therefore can treat the space as if it doesn't exist. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Eric Sandeen <sandeen@redhat.com>
2019-05-21 02:25:39 +08:00
/*
* The log is permanently allocated, so the space it occupies will
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
if (mp->m_sb.sb_logstart &&
XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno)
agblocks -= mp->m_sb.sb_logblocks;
xfs: use the actual AG length when reserving blocks We need to use the actual AG length when making per-AG reservations, since we could otherwise end up reserving more blocks out of the last AG than there are actual blocks. Complained-about-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
2017-01-04 10:39:33 +08:00
*ask += xfs_refcountbt_max_size(mp, agblocks);
xfs: preallocate blocks for worst-case btree expansion To gracefully handle the situation where a CoW operation turns a single refcount extent into a lot of tiny ones and then run out of space when a tree split has to happen, use the per-AG reserved block pool to pre-allocate all the space we'll ever need for a maximal btree. For a 4K block size, this only costs an overhead of 0.3% of available disk space. When reflink is enabled, we have an unfortunate problem with rmap -- since we can share a block billions of times, this means that the reverse mapping btree can expand basically infinitely. When an AG is so full that there are no free blocks with which to expand the rmapbt, the filesystem will shut down hard. This is rather annoying to the user, so use the AG reservation code to reserve a "reasonable" amount of space for rmap. We'll prevent reflinks and CoW operations if we think we're getting close to exhausting an AG's free space rather than shutting down, but this permanent reservation should be enough for "most" users. Hopefully. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> [hch@lst.de: ensure that we invalidate the freed btree buffer] Signed-off-by: Christoph Hellwig <hch@lst.de>
2016-10-04 00:11:44 +08:00
*used += tree_len;
return error;
}