linux/fs/xfs/xfs_alloc_btree.c

504 lines
13 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* 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.
*
* 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
*/
#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_ag.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 00:14:59 +01:00
#include "xfs_trace.h"
#include "xfs_cksum.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 length,
int *stat)
{
int error;
xfs_agblock_t bno;
XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
/* 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) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
return error;
}
if (bno == NULLAGBLOCK) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*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);
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*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);
xfs: invalidate allocbt blocks moved to the free list When we free a block from the alloc btree tree, we move it to the freelist held in the AGFL and mark it busy in the busy extent tree. This typically happens when we merge btree blocks. Once the transaction is committed and checkpointed, the block can remain on the free list for an indefinite amount of time. Now, this isn't the end of the world at this point - if the free list is shortened, the buffer is invalidated in the transaction that moves it back to free space. If the buffer is allocated as metadata from the free list, then all the modifications getted logged, and we have no issues, either. And if it gets allocated as userdata direct from the freelist, it gets invalidated and so will never get written. However, during the time it sits on the free list, pressure on the log can cause the AIL to be pushed and the buffer that covers the block gets pushed for write. IOWs, we end up writing a freed metadata block to disk. Again, this isn't the end of the world because we know from the above we are only writing to free space. The problem, however, is for validation callbacks. If the block was on old btree root block, then the level of the block is going to be higher than the current tree root, and so will fail validation. There may be other inconsistencies in the block as well, and currently we don't care because the block is in free space. Shutting down the filesystem because a freed block doesn't pass write validation, OTOH, is rather unfriendly. So, make sure we always invalidate buffers as they move from the free space trees to the free list so that we guarantee they never get written to disk while on the free list. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Phil White <pwhite@sgi.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-11-02 01:38:41 +01:00
xfs_trans_binval(cur->bc_tp, bp);
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)
{
ASSERT(rec->alloc.ar_startblock != 0);
key->alloc.ar_startblock = rec->alloc.ar_startblock;
key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
}
STATIC void
xfs_allocbt_init_rec_from_key(
union xfs_btree_key *key,
union xfs_btree_rec *rec)
{
ASSERT(key->alloc.ar_startblock != 0);
rec->alloc.ar_startblock = key->alloc.ar_startblock;
rec->alloc.ar_blockcount = key->alloc.ar_blockcount;
}
STATIC void
xfs_allocbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
ASSERT(cur->bc_rec.a.ar_startblock != 0);
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));
ASSERT(agf->agf_roots[cur->bc_btnum] != 0);
ptr->s = agf->agf_roots[cur->bc_btnum];
}
STATIC __int64_t
xfs_allocbt_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;
if (cur->bc_btnum == XFS_BTNUM_BNO) {
return (__int64_t)be32_to_cpu(kp->ar_startblock) -
rec->ar_startblock;
}
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 bool
xfs_allocbt_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;
unsigned int level;
/*
* magic number and level verification
*
* During growfs operations, we can't verify the exact level or owner as
* the perag is not fully initialised and hence not attached to the
* buffer. In this case, check against the maximum tree depth.
*
* Similarly, during log recovery we will have a perag structure
* attached, but the agf information will not yet have been initialised
* from the on disk AGF. Again, we can only check against maximum limits
* in this case.
*/
level = be16_to_cpu(block->bb_level);
switch (block->bb_magic) {
case cpu_to_be32(XFS_ABTB_CRC_MAGIC):
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
return false;
if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
return false;
if (pag &&
be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
return false;
/* fall through */
case cpu_to_be32(XFS_ABTB_MAGIC):
if (pag && pag->pagf_init) {
if (level >= pag->pagf_levels[XFS_BTNUM_BNOi])
return false;
} else if (level >= mp->m_ag_maxlevels)
return false;
break;
case cpu_to_be32(XFS_ABTC_CRC_MAGIC):
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
return false;
if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
return false;
if (pag &&
be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
return false;
/* fall through */
case cpu_to_be32(XFS_ABTC_MAGIC):
if (pag && pag->pagf_init) {
if (level >= pag->pagf_levels[XFS_BTNUM_CNTi])
return false;
} else if (level >= mp->m_ag_maxlevels)
return false;
break;
default:
return false;
}
/* numrecs verification */
if (be16_to_cpu(block->bb_numrecs) > mp->m_alloc_mxr[level != 0])
return false;
/* sibling pointer verification */
if (!block->bb_u.s.bb_leftsib ||
(be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks &&
block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK)))
return false;
if (!block->bb_u.s.bb_rightsib ||
(be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks &&
block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK)))
return false;
return true;
}
static void
xfs_allocbt_read_verify(
struct xfs_buf *bp)
{
if (!(xfs_btree_sblock_verify_crc(bp) &&
xfs_allocbt_verify(bp))) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
bp->b_target->bt_mount, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
static void
xfs_allocbt_write_verify(
struct xfs_buf *bp)
{
if (!xfs_allocbt_verify(bp)) {
trace_xfs_btree_corrupt(bp, _RET_IP_);
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
bp->b_target->bt_mount, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
xfs_btree_sblock_calc_crc(bp);
}
const struct xfs_buf_ops xfs_allocbt_buf_ops = {
.verify_read = xfs_allocbt_read_verify,
.verify_write = xfs_allocbt_write_verify,
};
#if defined(DEBUG) || defined(XFS_WARN)
STATIC int
xfs_allocbt_keys_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
union xfs_btree_key *k2)
{
if (cur->bc_btnum == XFS_BTNUM_BNO) {
return be32_to_cpu(k1->alloc.ar_startblock) <
be32_to_cpu(k2->alloc.ar_startblock);
} else {
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_allocbt_recs_inorder(
struct xfs_btree_cur *cur,
union xfs_btree_rec *r1,
union xfs_btree_rec *r2)
{
if (cur->bc_btnum == XFS_BTNUM_BNO) {
return be32_to_cpu(r1->alloc.ar_startblock) +
be32_to_cpu(r1->alloc.ar_blockcount) <=
be32_to_cpu(r2->alloc.ar_startblock);
} else {
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));
}
}
#endif /* DEBUG */
static const struct xfs_btree_ops xfs_allocbt_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_rec_from_key = xfs_allocbt_init_rec_from_key,
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
.key_diff = xfs_allocbt_key_diff,
.buf_ops = &xfs_allocbt_buf_ops,
#if defined(DEBUG) || defined(XFS_WARN)
.keys_inorder = xfs_allocbt_keys_inorder,
.recs_inorder = xfs_allocbt_recs_inorder,
#endif
};
/*
* 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_SLEEP);
cur->bc_tp = tp;
cur->bc_mp = mp;
cur->bc_btnum = btnum;
cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_ops = &xfs_allocbt_ops;
if (btnum == XFS_BTNUM_CNT) {
cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
} else {
cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
}
cur->bc_private.a.agbp = agbp;
cur->bc_private.a.agno = agno;
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));
}