AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-28 02:05:20 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
6bdcf26ade
linux_dsm_epyc7002/fs/xfs/libxfs/xfs_inode_fork.c
Christoph Hellwig 6bdcf26ade xfs: use a b+tree for the in-core extent list 
Replace the current linear list and the indirection array for the in-core
extent list with a b+tree to avoid the need for larger memory allocations
for the indirection array when lots of extents are present.  The current
extent list implementations leads to heavy pressure on the memory
allocator when modifying files with a high extent count, and can lead
to high latencies because of that.

The replacement is a b+tree with a few quirks.  The leaf nodes directly
store the extent record in two u64 values.  The encoding is a little bit
different from the existing in-core extent records so that the start
offset and length which are required for lookups can be retreived with
simple mask operations.  The inner nodes store a 64-bit key containing
the start offset in the first half of the node, and the pointers to the
next lower level in the second half.  In either case we walk the node
from the beginninig to the end and do a linear search, as that is more
efficient for the low number of cache lines touched during a search
(2 for the inner nodes, 4 for the leaf nodes) than a binary search.
We store termination markers (zero length for the leaf nodes, an
otherwise impossible high bit for the inner nodes) to terminate the key
list / records instead of storing a count to use the available cache
lines as efficiently as possible.

One quirk of the algorithm is that while we normally split a node half and
half like usual btree implementations we just spill over entries added at
the very end of the list to a new node on its own.  This means we get a
100% fill grade for the common cases of bulk insertion when reading an
inode into memory, and when only sequentially appending to a file.  The
downside is a slightly higher chance of splits on the first random
insertions.

Both insert and removal manually recurse into the lower levels, but
the bulk deletion of the whole tree is still implemented as a recursive
function call, although one limited by the overall depth and with very
little stack usage in every iteration.

For the first few extents we dynamically grow the list from a single
extent to the next powers of two until we have a first full leaf block
and that building the actual tree.

The code started out based on the generic lib/btree.c code from Joern
Engel based on earlier work from Peter Zijlstra, but has since been
rewritten beyond recognition.

Signed-off-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>
2017-11-06 11:53:41 -08:00

834 lines
23 KiB
C
Raw Blame History

/*
* Copyright (c) 2000-2006 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 <linux/log2.h>
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_attr_sf.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_ifork_zone;
STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);
static inline dev_t xfs_to_linux_dev_t(xfs_dev_t dev)
{
return MKDEV(sysv_major(dev) & 0x1ff, sysv_minor(dev));
}
/*
* Copy inode type and data and attr format specific information from the
* on-disk inode to the in-core inode and fork structures. For fifos, devices,
* and sockets this means set i_rdev to the proper value. For files,
* directories, and symlinks this means to bring in the in-line data or extent
* pointers as well as the attribute fork. For a fork in B-tree format, only
* the root is immediately brought in-core. The rest will be read in later when
* first referenced (see xfs_iread_extents()).
*/
int
xfs_iformat_fork(
struct xfs_inode *ip,
struct xfs_dinode *dip)
{
struct inode *inode = VFS_I(ip);
struct xfs_attr_shortform *atp;
int size;
int error = 0;
xfs_fsize_t di_size;
if (unlikely(be32_to_cpu(dip->di_nextents) +
be16_to_cpu(dip->di_anextents) >
be64_to_cpu(dip->di_nblocks))) {
xfs_warn(ip->i_mount,
"corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
(unsigned long long)ip->i_ino,
(int)(be32_to_cpu(dip->di_nextents) +
be16_to_cpu(dip->di_anextents)),
(unsigned long long)
be64_to_cpu(dip->di_nblocks));
XFS_CORRUPTION_ERROR("xfs_iformat(1)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
if (unlikely(dip->di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
xfs_warn(ip->i_mount, "corrupt dinode %Lu, forkoff = 0x%x.",
(unsigned long long)ip->i_ino,
dip->di_forkoff);
XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
!ip->i_mount->m_rtdev_targp)) {
xfs_warn(ip->i_mount,
"corrupt dinode %Lu, has realtime flag set.",
ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
XFS_ERRLEVEL_LOW, ip->i_mount, dip);
return -EFSCORRUPTED;
}
if (unlikely(xfs_is_reflink_inode(ip) && !S_ISREG(inode->i_mode))) {
xfs_warn(ip->i_mount,
"corrupt dinode %llu, wrong file type for reflink.",
ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(reflink)",
XFS_ERRLEVEL_LOW, ip->i_mount, dip);
return -EFSCORRUPTED;
}
if (unlikely(xfs_is_reflink_inode(ip) &&
(ip->i_d.di_flags & XFS_DIFLAG_REALTIME))) {
xfs_warn(ip->i_mount,
"corrupt dinode %llu, has reflink+realtime flag set.",
ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(reflink)",
XFS_ERRLEVEL_LOW, ip->i_mount, dip);
return -EFSCORRUPTED;
}
switch (inode->i_mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
if (unlikely(dip->di_format != XFS_DINODE_FMT_DEV)) {
XFS_CORRUPTION_ERROR("xfs_iformat(3)", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
ip->i_d.di_size = 0;
inode->i_rdev = xfs_to_linux_dev_t(xfs_dinode_get_rdev(dip));
break;
case S_IFREG:
case S_IFLNK:
case S_IFDIR:
switch (dip->di_format) {
case XFS_DINODE_FMT_LOCAL:
/*
* no local regular files yet
*/
if (unlikely(S_ISREG(be16_to_cpu(dip->di_mode)))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (local format for regular file).",
(unsigned long long) ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat(4)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
di_size = be64_to_cpu(dip->di_size);
if (unlikely(di_size < 0 ||
di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad size %Ld for local inode).",
(unsigned long long) ip->i_ino,
(long long) di_size);
XFS_CORRUPTION_ERROR("xfs_iformat(5)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
size = (int)di_size;
error = xfs_iformat_local(ip, dip, XFS_DATA_FORK, size);
break;
case XFS_DINODE_FMT_EXTENTS:
error = xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
break;
case XFS_DINODE_FMT_BTREE:
error = xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
break;
default:
XFS_ERROR_REPORT("xfs_iformat(6)", XFS_ERRLEVEL_LOW,
ip->i_mount);
return -EFSCORRUPTED;
}
break;
default:
XFS_ERROR_REPORT("xfs_iformat(7)", XFS_ERRLEVEL_LOW, ip->i_mount);
return -EFSCORRUPTED;
}
if (error)
return error;
/* Check inline dir contents. */
if (S_ISDIR(inode->i_mode) && dip->di_format == XFS_DINODE_FMT_LOCAL) {
error = xfs_dir2_sf_verify(ip);
if (error) {
xfs_idestroy_fork(ip, XFS_DATA_FORK);
return error;
}
}
if (xfs_is_reflink_inode(ip)) {
ASSERT(ip->i_cowfp == NULL);
xfs_ifork_init_cow(ip);
}
if (!XFS_DFORK_Q(dip))
return 0;
ASSERT(ip->i_afp == NULL);
ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP | KM_NOFS);
switch (dip->di_aformat) {
case XFS_DINODE_FMT_LOCAL:
atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
size = be16_to_cpu(atp->hdr.totsize);
if (unlikely(size < sizeof(struct xfs_attr_sf_hdr))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad attr fork size %Ld).",
(unsigned long long) ip->i_ino,
(long long) size);
XFS_CORRUPTION_ERROR("xfs_iformat(8)",
XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
error = -EFSCORRUPTED;
break;
}
error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, size);
break;
case XFS_DINODE_FMT_EXTENTS:
error = xfs_iformat_extents(ip, dip, XFS_ATTR_FORK);
break;
case XFS_DINODE_FMT_BTREE:
error = xfs_iformat_btree(ip, dip, XFS_ATTR_FORK);
break;
default:
error = -EFSCORRUPTED;
break;
}
if (error) {
kmem_zone_free(xfs_ifork_zone, ip->i_afp);
ip->i_afp = NULL;
if (ip->i_cowfp)
kmem_zone_free(xfs_ifork_zone, ip->i_cowfp);
ip->i_cowfp = NULL;
xfs_idestroy_fork(ip, XFS_DATA_FORK);
}
return error;
}
void
xfs_init_local_fork(
struct xfs_inode *ip,
int whichfork,
const void *data,
int size)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
int mem_size = size, real_size = 0;
bool zero_terminate;
/*
* If we are using the local fork to store a symlink body we need to
* zero-terminate it so that we can pass it back to the VFS directly.
* Overallocate the in-memory fork by one for that and add a zero
* to terminate it below.
*/
zero_terminate = S_ISLNK(VFS_I(ip)->i_mode);
if (zero_terminate)
mem_size++;
if (size) {
real_size = roundup(mem_size, 4);
ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP | KM_NOFS);
memcpy(ifp->if_u1.if_data, data, size);
if (zero_terminate)
ifp->if_u1.if_data[size] = '\0';
} else {
ifp->if_u1.if_data = NULL;
}
ifp->if_bytes = size;
ifp->if_real_bytes = real_size;
ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
ifp->if_flags |= XFS_IFINLINE;
}
/*
* The file is in-lined in the on-disk inode.
*/
STATIC int
xfs_iformat_local(
xfs_inode_t *ip,
xfs_dinode_t *dip,
int whichfork,
int size)
{
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
* kmem_alloc() or memcpy() below.
*/
if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
xfs_warn(ip->i_mount,
"corrupt inode %Lu (bad size %d for local fork, size = %d).",
(unsigned long long) ip->i_ino, size,
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
XFS_CORRUPTION_ERROR("xfs_iformat_local", XFS_ERRLEVEL_LOW,
ip->i_mount, dip);
return -EFSCORRUPTED;
}
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
/*
* The file consists of a set of extents all of which fit into the on-disk
* inode.
*/
STATIC int
xfs_iformat_extents(
struct xfs_inode *ip,
struct xfs_dinode *dip,
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
int state = xfs_bmap_fork_to_state(whichfork);
int nex = XFS_DFORK_NEXTENTS(dip, whichfork);
int size = nex * sizeof(xfs_bmbt_rec_t);
struct xfs_iext_cursor icur;
struct xfs_bmbt_rec *dp;
struct xfs_bmbt_irec new;
int i;
/*
* If the number of extents is unreasonable, then something is wrong and
* we just bail out rather than crash in kmem_alloc() or memcpy() below.
*/
if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
(unsigned long long) ip->i_ino, nex);
XFS_CORRUPTION_ERROR("xfs_iformat_extents(1)", XFS_ERRLEVEL_LOW,
mp, dip);
return -EFSCORRUPTED;
}
ifp->if_real_bytes = 0;
ifp->if_bytes = 0;
ifp->if_u1.if_root = NULL;
ifp->if_height = 0;
if (size) {
dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
xfs_iext_first(ifp, &icur);
for (i = 0; i < nex; i++, dp++) {
if (!xfs_bmbt_validate_extent(mp, whichfork, dp)) {
XFS_ERROR_REPORT("xfs_iformat_extents(2)",
XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
}
xfs_bmbt_disk_get_all(dp, &new);
xfs_iext_insert(ip, &icur, 1, &new, state);
trace_xfs_read_extent(ip, &icur, state, _THIS_IP_);
xfs_iext_next(ifp, &icur);
}
}
ifp->if_flags |= XFS_IFEXTENTS;
return 0;
}
/*
* The file has too many extents to fit into
* the inode, so they are in B-tree format.
* Allocate a buffer for the root of the B-tree
* and copy the root into it. The i_extents
* field will remain NULL until all of the
* extents are read in (when they are needed).
*/
STATIC int
xfs_iformat_btree(
xfs_inode_t *ip,
xfs_dinode_t *dip,
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
xfs_bmdr_block_t *dfp;
xfs_ifork_t *ifp;
/* REFERENCED */
int nrecs;
int size;
int level;
ifp = XFS_IFORK_PTR(ip, whichfork);
dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
size = XFS_BMAP_BROOT_SPACE(mp, dfp);
nrecs = be16_to_cpu(dfp->bb_numrecs);
level = be16_to_cpu(dfp->bb_level);
/*
* blow out if -- fork has less extents than can fit in
* fork (fork shouldn't be a btree format), root btree
* block has more records than can fit into the fork,
* or the number of extents is greater than the number of
* blocks.
*/
if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <=
XFS_IFORK_MAXEXT(ip, whichfork) ||
XFS_BMDR_SPACE_CALC(nrecs) >
XFS_DFORK_SIZE(dip, mp, whichfork) ||
XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks) ||
level == 0 || level > XFS_BTREE_MAXLEVELS) {
xfs_warn(mp, "corrupt inode %Lu (btree).",
(unsigned long long) ip->i_ino);
XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
mp, dip);
return -EFSCORRUPTED;
}
ifp->if_broot_bytes = size;
ifp->if_broot = kmem_alloc(size, KM_SLEEP | KM_NOFS);
ASSERT(ifp->if_broot != NULL);
/*
* Copy and convert from the on-disk structure
* to the in-memory structure.
*/
xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
ifp->if_broot, size);
ifp->if_flags &= ~XFS_IFEXTENTS;
ifp->if_flags |= XFS_IFBROOT;
ifp->if_real_bytes = 0;
ifp->if_bytes = 0;
ifp->if_u1.if_root = NULL;
ifp->if_height = 0;
return 0;
}
/*
* Reallocate the space for if_broot based on the number of records
* being added or deleted as indicated in rec_diff. Move the records
* and pointers in if_broot to fit the new size. When shrinking this
* will eliminate holes between the records and pointers created by
* the caller. When growing this will create holes to be filled in
* by the caller.
*
* The caller must not request to add more records than would fit in
* the on-disk inode root. If the if_broot is currently NULL, then
* if we are adding records, one will be allocated. The caller must also
* not request that the number of records go below zero, although
* it can go to zero.
*
* ip -- the inode whose if_broot area is changing
* ext_diff -- the change in the number of records, positive or negative,
* requested for the if_broot array.
*/
void
xfs_iroot_realloc(
xfs_inode_t *ip,
int rec_diff,
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
int cur_max;
xfs_ifork_t *ifp;
struct xfs_btree_block *new_broot;
int new_max;
size_t new_size;
char *np;
char *op;
/*
* Handle the degenerate case quietly.
*/
if (rec_diff == 0) {
return;
}
ifp = XFS_IFORK_PTR(ip, whichfork);
if (rec_diff > 0) {
/*
* If there wasn't any memory allocated before, just
* allocate it now and get out.
*/
if (ifp->if_broot_bytes == 0) {
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, rec_diff);
ifp->if_broot = kmem_alloc(new_size, KM_SLEEP | KM_NOFS);
ifp->if_broot_bytes = (int)new_size;
return;
}
/*
* If there is already an existing if_broot, then we need
* to realloc() it and shift the pointers to their new
* location. The records don't change location because
* they are kept butted up against the btree block header.
*/
cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
new_max = cur_max + rec_diff;
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
ifp->if_broot = kmem_realloc(ifp->if_broot, new_size,
KM_SLEEP | KM_NOFS);
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
ifp->if_broot_bytes);
np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
(int)new_size);
ifp->if_broot_bytes = (int)new_size;
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
XFS_IFORK_SIZE(ip, whichfork));
memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t));
return;
}
/*
* rec_diff is less than 0. In this case, we are shrinking the
* if_broot buffer. It must already exist. If we go to zero
* records, just get rid of the root and clear the status bit.
*/
ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0));
cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
new_max = cur_max + rec_diff;
ASSERT(new_max >= 0);
if (new_max > 0)
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
else
new_size = 0;
if (new_size > 0) {
new_broot = kmem_alloc(new_size, KM_SLEEP | KM_NOFS);
/*
* First copy over the btree block header.
*/
memcpy(new_broot, ifp->if_broot,
XFS_BMBT_BLOCK_LEN(ip->i_mount));
} else {
new_broot = NULL;
ifp->if_flags &= ~XFS_IFBROOT;
}
/*
* Only copy the records and pointers if there are any.
*/
if (new_max > 0) {
/*
* First copy the records.
*/
op = (char *)XFS_BMBT_REC_ADDR(mp, ifp->if_broot, 1);
np = (char *)XFS_BMBT_REC_ADDR(mp, new_broot, 1);
memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_rec_t));
/*
* Then copy the pointers.
*/
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
ifp->if_broot_bytes);
np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, new_broot, 1,
(int)new_size);
memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t));
}
kmem_free(ifp->if_broot);
ifp->if_broot = new_broot;
ifp->if_broot_bytes = (int)new_size;
if (ifp->if_broot)
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
XFS_IFORK_SIZE(ip, whichfork));
return;
}
/*
* This is called when the amount of space needed for if_data
* is increased or decreased. The change in size is indicated by
* the number of bytes that need to be added or deleted in the
* byte_diff parameter.
*
* If the amount of space needed has decreased below the size of the
* inline buffer, then switch to using the inline buffer. Otherwise,
* use kmem_realloc() or kmem_alloc() to adjust the size of the buffer
* to what is needed.
*
* ip -- the inode whose if_data area is changing
* byte_diff -- the change in the number of bytes, positive or negative,
* requested for the if_data array.
*/
void
xfs_idata_realloc(
xfs_inode_t *ip,
int byte_diff,
int whichfork)
{
xfs_ifork_t *ifp;
int new_size;
int real_size;
if (byte_diff == 0) {
return;
}
ifp = XFS_IFORK_PTR(ip, whichfork);
new_size = (int)ifp->if_bytes + byte_diff;
ASSERT(new_size >= 0);
if (new_size == 0) {
kmem_free(ifp->if_u1.if_data);
ifp->if_u1.if_data = NULL;
real_size = 0;
} else {
/*
* Stuck with malloc/realloc.
* For inline data, the underlying buffer must be
* a multiple of 4 bytes in size so that it can be
* logged and stay on word boundaries. We enforce
* that here.
*/
real_size = roundup(new_size, 4);
if (ifp->if_u1.if_data == NULL) {
ASSERT(ifp->if_real_bytes == 0);
ifp->if_u1.if_data = kmem_alloc(real_size,
KM_SLEEP | KM_NOFS);
} else {
/*
* Only do the realloc if the underlying size
* is really changing.
*/
if (ifp->if_real_bytes != real_size) {
ifp->if_u1.if_data =
kmem_realloc(ifp->if_u1.if_data,
real_size,
KM_SLEEP | KM_NOFS);
}
}
}
ifp->if_real_bytes = real_size;
ifp->if_bytes = new_size;
ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
}
void
xfs_idestroy_fork(
xfs_inode_t *ip,
int whichfork)
{
xfs_ifork_t *ifp;
ifp = XFS_IFORK_PTR(ip, whichfork);
if (ifp->if_broot != NULL) {
kmem_free(ifp->if_broot);
ifp->if_broot = NULL;
}
/*
* If the format is local, then we can't have an extents
* array so just look for an inline data array. If we're
* not local then we may or may not have an extents list,
* so check and free it up if we do.
*/
if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
if (ifp->if_u1.if_data != NULL) {
ASSERT(ifp->if_real_bytes != 0);
kmem_free(ifp->if_u1.if_data);
ifp->if_u1.if_data = NULL;
ifp->if_real_bytes = 0;
}
} else if ((ifp->if_flags & XFS_IFEXTENTS) && ifp->if_height) {
xfs_iext_destroy(ifp);
}
ASSERT(ifp->if_real_bytes == 0);
if (whichfork == XFS_ATTR_FORK) {
kmem_zone_free(xfs_ifork_zone, ip->i_afp);
ip->i_afp = NULL;
} else if (whichfork == XFS_COW_FORK) {
kmem_zone_free(xfs_ifork_zone, ip->i_cowfp);
ip->i_cowfp = NULL;
}
}
/*
* Convert in-core extents to on-disk form
*
* In the case of the data fork, the in-core and on-disk fork sizes can be
* different due to delayed allocation extents. We only copy on-disk extents
* here, so callers must always use the physical fork size to determine the
* size of the buffer passed to this routine. We will return the size actually
* used.
*/
int
xfs_iextents_copy(
struct xfs_inode *ip,
struct xfs_bmbt_rec *dp,
int whichfork)
{
int state = xfs_bmap_fork_to_state(whichfork);
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec rec;
int copied = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
ASSERT(ifp->if_bytes > 0);
for_each_xfs_iext(ifp, &icur, &rec) {
if (isnullstartblock(rec.br_startblock))
continue;
xfs_bmbt_disk_set_all(dp, &rec);
trace_xfs_write_extent(ip, &icur, state, _RET_IP_);
ASSERT(xfs_bmbt_validate_extent(ip->i_mount, whichfork, dp));
copied += sizeof(struct xfs_bmbt_rec);
dp++;
}
ASSERT(copied > 0);
ASSERT(copied <= ifp->if_bytes);
return copied;
}
/*
* Each of the following cases stores data into the same region
* of the on-disk inode, so only one of them can be valid at
* any given time. While it is possible to have conflicting formats
* and log flags, e.g. having XFS_ILOG_?DATA set when the fork is
* in EXTENTS format, this can only happen when the fork has
* changed formats after being modified but before being flushed.
* In these cases, the format always takes precedence, because the
* format indicates the current state of the fork.
*/
void
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
xfs_inode_log_item_t *iip,
int whichfork)
{
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
{ XFS_ILOG_DDATA, XFS_ILOG_ADATA };
static const short extflag[2] =
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
if (!iip)
return;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
* for the attribute fork.
*/
if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
return;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
switch (XFS_IFORK_FORMAT(ip, whichfork)) {
case XFS_DINODE_FMT_LOCAL:
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
}
break;
case XFS_DINODE_FMT_EXTENTS:
ASSERT((ifp->if_flags & XFS_IFEXTENTS) ||
!(iip->ili_fields & extflag[whichfork]));
if ((iip->ili_fields & extflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) > 0);
(void)xfs_iextents_copy(ip, (xfs_bmbt_rec_t *)cp,
whichfork);
}
break;
case XFS_DINODE_FMT_BTREE:
if ((iip->ili_fields & brootflag[whichfork]) &&
(ifp->if_broot_bytes > 0)) {
ASSERT(ifp->if_broot != NULL);
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
XFS_IFORK_SIZE(ip, whichfork));
xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes,
(xfs_bmdr_block_t *)cp,
XFS_DFORK_SIZE(dip, mp, whichfork));
}
break;
case XFS_DINODE_FMT_DEV:
if (iip->ili_fields & XFS_ILOG_DEV) {
ASSERT(whichfork == XFS_DATA_FORK);
xfs_dinode_put_rdev(dip, sysv_encode_dev(VFS_I(ip)->i_rdev));
}
break;
default:
ASSERT(0);
break;
}
}
/* Convert bmap state flags to an inode fork. */
struct xfs_ifork *
xfs_iext_state_to_fork(
struct xfs_inode *ip,
int state)
{
if (state & BMAP_COWFORK)
return ip->i_cowfp;
else if (state & BMAP_ATTRFORK)
return ip->i_afp;
return &ip->i_df;
}
/*
* Initialize an inode's copy-on-write fork.
*/
void
xfs_ifork_init_cow(
struct xfs_inode *ip)
{
if (ip->i_cowfp)
return;
ip->i_cowfp = kmem_zone_zalloc(xfs_ifork_zone,
KM_SLEEP | KM_NOFS);
ip->i_cowfp->if_flags = XFS_IFEXTENTS;
ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
ip->i_cnextents = 0;
}
Reference in New Issue View Git Blame Copy Permalink