linux/fs/xfs/libxfs/xfs_alloc_btree.c

542 lines
13 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_error.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs_trace.h"
#include "xfs_trans.h"
STATIC struct xfs_btree_cur *
xfs_allocbt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_allocbt_init_cursor(cur->bc_mp, cur->bc_tp,
cur->bc_private.a.agbp, cur->bc_private.a.agno,
cur->bc_btnum);
}
STATIC void
xfs_allocbt_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);
int btnum = cur->bc_btnum;
struct xfs_perag *pag = xfs_perag_get(cur->bc_mp, seqno);
ASSERT(ptr->s != 0);
agf->agf_roots[btnum] = ptr->s;
be32_add_cpu(&agf->agf_levels[btnum], inc);
pag->pagf_levels[btnum] += inc;
xfs_perag_put(pag);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
}
STATIC int
xfs_allocbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
int *stat)
{
int error;
xfs_agblock_t bno;
/* Allocate the new block from the freelist. If we can't, give up. */
error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_private.a.agbp,
&bno, 1);
if (error)
return error;
if (bno == NULLAGBLOCK) {
*stat = 0;
return 0;
}
xfs_extent_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false);
xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
*stat = 1;
return 0;
}
STATIC int
xfs_allocbt_free_block(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
struct xfs_buf *agbp = cur->bc_private.a.agbp;
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
xfs_agblock_t bno;
int error;
bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp));
error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
if (error)
return error;
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
xfs_trans_agbtree_delta(cur->bc_tp, -1);
return 0;
}
/*
* Update the longest extent in the AGF
*/
STATIC void
xfs_allocbt_update_lastrec(
struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
union xfs_btree_rec *rec,
int ptr,
int reason)
{
struct xfs_agf *agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
xfs_agnumber_t seqno = be32_to_cpu(agf->agf_seqno);
struct xfs_perag *pag;
__be32 len;
int numrecs;
ASSERT(cur->bc_btnum == XFS_BTNUM_CNT);
switch (reason) {
case LASTREC_UPDATE:
/*
* If this is the last leaf block and it's the last record,
* then update the size of the longest extent in the AG.
*/
if (ptr != xfs_btree_get_numrecs(block))
return;
len = rec->alloc.ar_blockcount;
break;
case LASTREC_INSREC:
if (be32_to_cpu(rec->alloc.ar_blockcount) <=
be32_to_cpu(agf->agf_longest))
return;
len = rec->alloc.ar_blockcount;
break;
case LASTREC_DELREC:
numrecs = xfs_btree_get_numrecs(block);
if (ptr <= numrecs)
return;
ASSERT(ptr == numrecs + 1);
if (numrecs) {
xfs_alloc_rec_t *rrp;
rrp = XFS_ALLOC_REC_ADDR(cur->bc_mp, block, numrecs);
len = rrp->ar_blockcount;
} else {
len = 0;
}
break;
default:
ASSERT(0);
return;
}
agf->agf_longest = len;
pag = xfs_perag_get(cur->bc_mp, seqno);
pag->pagf_longest = be32_to_cpu(len);
xfs_perag_put(pag);
xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp, XFS_AGF_LONGEST);
}
STATIC int
xfs_allocbt_get_minrecs(
struct xfs_btree_cur *cur,
int level)
{
return cur->bc_mp->m_alloc_mnr[level != 0];
}
STATIC int
xfs_allocbt_get_maxrecs(
struct xfs_btree_cur *cur,
int level)
{
return cur->bc_mp->m_alloc_mxr[level != 0];
}
STATIC void
xfs_allocbt_init_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
key->alloc.ar_startblock = rec->alloc.ar_startblock;
key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
}
STATIC void
xfs_bnobt_init_high_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
__u32 x;
x = be32_to_cpu(rec->alloc.ar_startblock);
x += be32_to_cpu(rec->alloc.ar_blockcount) - 1;
key->alloc.ar_startblock = cpu_to_be32(x);
key->alloc.ar_blockcount = 0;
}
STATIC void
xfs_cntbt_init_high_key_from_rec(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
key->alloc.ar_startblock = 0;
}
STATIC void
xfs_allocbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
rec->alloc.ar_startblock = cpu_to_be32(cur->bc_rec.a.ar_startblock);
rec->alloc.ar_blockcount = cpu_to_be32(cur->bc_rec.a.ar_blockcount);
}
STATIC void
xfs_allocbt_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_roots[cur->bc_btnum];
}
STATIC int64_t
xfs_bnobt_key_diff(
struct xfs_btree_cur *cur,
union xfs_btree_key *key)
{
xfs_alloc_rec_incore_t *rec = &cur->bc_rec.a;
xfs_alloc_key_t *kp = &key->alloc;
return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
}
STATIC int64_t
xfs_cntbt_key_diff(
struct xfs_btree_cur *cur,
union xfs_btree_key *key)
{
xfs_alloc_rec_incore_t *rec = &cur->bc_rec.a;
xfs_alloc_key_t *kp = &key->alloc;
int64_t diff;
diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
if (diff)
return diff;
return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
}
STATIC int64_t
xfs_bnobt_diff_two_keys(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
be32_to_cpu(k2->alloc.ar_startblock);
}
STATIC int64_t
xfs_cntbt_diff_two_keys(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
int64_t diff;
diff = be32_to_cpu(k1->alloc.ar_blockcount) -
be32_to_cpu(k2->alloc.ar_blockcount);
if (diff)
return diff;
return be32_to_cpu(k1->alloc.ar_startblock) -
be32_to_cpu(k2->alloc.ar_startblock);
}
static xfs_failaddr_t
xfs_allocbt_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
struct xfs_perag *pag = bp->b_pag;
xfs_failaddr_t fa;
unsigned int level;
xfs_btnum_t btnum = XFS_BTNUM_BNOi;
if (!xfs_verify_magic(bp, block->bb_magic))
return __this_address;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
fa = xfs_btree_sblock_v5hdr_verify(bp);
if (fa)
return fa;
}
/*
* The perag may not be attached during grow operations or fully
* initialized from the AGF during log recovery. Therefore we can only
* check against maximum tree depth from those contexts.
*
* Otherwise check against the per-tree limit. Peek at one of the
* verifier magic values to determine the type of tree we're verifying
* against.
*/
level = be16_to_cpu(block->bb_level);
if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
btnum = XFS_BTNUM_CNTi;
if (pag && pag->pagf_init) {
if (level >= pag->pagf_levels[btnum])
return __this_address;
} else if (level >= mp->m_ag_maxlevels)
return __this_address;
return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]);
}
static void
xfs_allocbt_read_verify(
struct xfs_buf *bp)
{
xfs_failaddr_t fa;
if (!xfs_btree_sblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_allocbt_verify(bp);
if (fa)
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
}
if (bp->b_error)
trace_xfs_btree_corrupt(bp, _RET_IP_);
}
static void
xfs_allocbt_write_verify(
struct xfs_buf *bp)
{
xfs_failaddr_t fa;
fa = xfs_allocbt_verify(bp);
if (fa) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
xfs_btree_sblock_calc_crc(bp);
}
const struct xfs_buf_ops xfs_bnobt_buf_ops = {
.name = "xfs_bnobt",
.magic = { cpu_to_be32(XFS_ABTB_MAGIC),
cpu_to_be32(XFS_ABTB_CRC_MAGIC) },
.verify_read = xfs_allocbt_read_verify,
.verify_write = xfs_allocbt_write_verify,
.verify_struct = xfs_allocbt_verify,
};
const struct xfs_buf_ops xfs_cntbt_buf_ops = {
.name = "xfs_cntbt",
.magic = { cpu_to_be32(XFS_ABTC_MAGIC),
cpu_to_be32(XFS_ABTC_CRC_MAGIC) },
.verify_read = xfs_allocbt_read_verify,
.verify_write = xfs_allocbt_write_verify,
.verify_struct = xfs_allocbt_verify,
};
STATIC int
xfs_bnobt_keys_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
return be32_to_cpu(k1->alloc.ar_startblock) <
be32_to_cpu(k2->alloc.ar_startblock);
}
STATIC int
xfs_bnobt_recs_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_rec *r1,
union xfs_btree_rec *r2)
{
return be32_to_cpu(r1->alloc.ar_startblock) +
be32_to_cpu(r1->alloc.ar_blockcount) <=
be32_to_cpu(r2->alloc.ar_startblock);
}
STATIC int
xfs_cntbt_keys_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
return be32_to_cpu(k1->alloc.ar_blockcount) <
be32_to_cpu(k2->alloc.ar_blockcount) ||
(k1->alloc.ar_blockcount == k2->alloc.ar_blockcount &&
be32_to_cpu(k1->alloc.ar_startblock) <
be32_to_cpu(k2->alloc.ar_startblock));
}
STATIC int
xfs_cntbt_recs_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_rec *r1,
union xfs_btree_rec *r2)
{
return be32_to_cpu(r1->alloc.ar_blockcount) <
be32_to_cpu(r2->alloc.ar_blockcount) ||
(r1->alloc.ar_blockcount == r2->alloc.ar_blockcount &&
be32_to_cpu(r1->alloc.ar_startblock) <
be32_to_cpu(r2->alloc.ar_startblock));
}
static const struct xfs_btree_ops xfs_bnobt_ops = {
.rec_len = sizeof(xfs_alloc_rec_t),
.key_len = sizeof(xfs_alloc_key_t),
.dup_cursor = xfs_allocbt_dup_cursor,
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
.update_lastrec = xfs_allocbt_update_lastrec,
.get_minrecs = xfs_allocbt_get_minrecs,
.get_maxrecs = xfs_allocbt_get_maxrecs,
.init_key_from_rec = xfs_allocbt_init_key_from_rec,
.init_high_key_from_rec = xfs_bnobt_init_high_key_from_rec,
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
.key_diff = xfs_bnobt_key_diff,
.buf_ops = &xfs_bnobt_buf_ops,
.diff_two_keys = xfs_bnobt_diff_two_keys,
.keys_inorder = xfs_bnobt_keys_inorder,
.recs_inorder = xfs_bnobt_recs_inorder,
};
static const struct xfs_btree_ops xfs_cntbt_ops = {
.rec_len = sizeof(xfs_alloc_rec_t),
.key_len = sizeof(xfs_alloc_key_t),
.dup_cursor = xfs_allocbt_dup_cursor,
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
.update_lastrec = xfs_allocbt_update_lastrec,
.get_minrecs = xfs_allocbt_get_minrecs,
.get_maxrecs = xfs_allocbt_get_maxrecs,
.init_key_from_rec = xfs_allocbt_init_key_from_rec,
.init_high_key_from_rec = xfs_cntbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
.key_diff = xfs_cntbt_key_diff,
.buf_ops = &xfs_cntbt_buf_ops,
.diff_two_keys = xfs_cntbt_diff_two_keys,
.keys_inorder = xfs_cntbt_keys_inorder,
.recs_inorder = xfs_cntbt_recs_inorder,
};
/*
* Allocate a new allocation btree cursor.
*/
struct xfs_btree_cur * /* new alloc btree cursor */
xfs_allocbt_init_cursor(
struct xfs_mount *mp, /* file system mount point */
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *agbp, /* buffer for agf structure */
xfs_agnumber_t agno, /* allocation group number */
xfs_btnum_t btnum) /* btree identifier */
{
struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
struct xfs_btree_cur *cur;
ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
cur->bc_tp = tp;
cur->bc_mp = mp;
cur->bc_btnum = btnum;
cur->bc_blocklog = mp->m_sb.sb_blocklog;
if (btnum == XFS_BTNUM_CNT) {
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
cur->bc_ops = &xfs_cntbt_ops;
cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
} else {
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
cur->bc_ops = &xfs_bnobt_ops;
cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
}
cur->bc_private.a.agbp = agbp;
cur->bc_private.a.agno = agno;
cur->bc_private.a.priv.abt.active = false;
if (xfs_sb_version_hascrc(&mp->m_sb))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
return cur;
}
/*
* Calculate number of records in an alloc btree block.
*/
int
xfs_allocbt_maxrecs(
struct xfs_mount *mp,
int blocklen,
int leaf)
{
blocklen -= XFS_ALLOC_BLOCK_LEN(mp);
if (leaf)
return blocklen / sizeof(xfs_alloc_rec_t);
return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
}
/* Calculate the freespace btree size for some records. */
xfs_extlen_t
xfs_allocbt_calc_size(
struct xfs_mount *mp,
unsigned long long len)
{
return xfs_btree_calc_size(mp->m_alloc_mnr, len);
}