lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

xfs: create xfs_bmap_util.[ch]

Browse Source 
There is a bunch of code in xfs_bmap.c that is kernel specific and
not shared with userspace. To minimise the difference between the
kernel and userspace code, shift this unshared code to
xfs_bmap_util.c, and the declarations to xfs_bmap_util.h.

The biggest issue here is xfs_bmap_finish() - userspace has it's own
definition of this function, and so we need to move it out of
xfs_bmap.[ch]. This means several other files need to include
xfs_bmap_util.h as well.

It also introduces and interesting dance for the stack switching
code in xfs_bmapi_allocate(). The stack switching/workqueue code is
actually moved to xfs_bmap_util.c, so that userspace can simply use
a #define in a header file to connect the dots without needing to
know about the stack switch code at all.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
This commit is contained in:
Dave Chinner
2013-08-12 20:49:42 +10:00
committed by Ben Myers
parent ff55068c20
commit 6898811459
20 changed files with 957 additions and 853 deletions
Download Patch File Download Diff File Expand all files Collapse all files

804
fs/xfs/xfs_bmap.c
View File

@@ -40,6 +40,7 @@
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_attr_leaf.h"
@@ -109,19 +110,6 @@ xfs_bmap_compute_maxlevels(
mp->m_bm_maxlevels[whichfork] = level;
}
/*
* Convert the given file system block to a disk block. We have to treat it
* differently based on whether the file is a real time file or not, because the
* bmap code does.
*/
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
return (XFS_IS_REALTIME_INODE(ip) ? \
(xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
}
STATIC int /* error */
xfs_bmbt_lookup_eq(
struct xfs_btree_cur *cur,
@@ -263,173 +251,6 @@ xfs_bmap_forkoff_reset(
}
}
/*
* Extent tree block counting routines.
*/
/*
* Count leaf blocks given a range of extent records.
*/
STATIC void
xfs_bmap_count_leaves(
xfs_ifork_t *ifp,
xfs_extnum_t idx,
int numrecs,
int *count)
{
int b;
for (b = 0; b < numrecs; b++) {
xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
*count += xfs_bmbt_get_blockcount(frp);
}
}
/*
* Count leaf blocks given a range of extent records originally
* in btree format.
*/
STATIC void
xfs_bmap_disk_count_leaves(
struct xfs_mount *mp,
struct xfs_btree_block *block,
int numrecs,
int *count)
{
int b;
xfs_bmbt_rec_t *frp;
for (b = 1; b <= numrecs; b++) {
frp = XFS_BMBT_REC_ADDR(mp, block, b);
*count += xfs_bmbt_disk_get_blockcount(frp);
}
}
/*
* Recursively walks each level of a btree
* to count total fsblocks is use.
*/
STATIC int /* error */
xfs_bmap_count_tree(
xfs_mount_t *mp, /* file system mount point */
xfs_trans_t *tp, /* transaction pointer */
xfs_ifork_t *ifp, /* inode fork pointer */
xfs_fsblock_t blockno, /* file system block number */
int levelin, /* level in btree */
int *count) /* Count of blocks */
{
int error;
xfs_buf_t *bp, *nbp;
int level = levelin;
__be64 *pp;
xfs_fsblock_t bno = blockno;
xfs_fsblock_t nextbno;
struct xfs_btree_block *block, *nextblock;
int numrecs;
error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
block = XFS_BUF_TO_BLOCK(bp);
if (--level) {
/* Not at node above leaves, count this level of nodes */
nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
while (nextbno != NULLFSBLOCK) {
error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
nextblock = XFS_BUF_TO_BLOCK(nbp);
nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
xfs_trans_brelse(tp, nbp);
}
/* Dive to the next level */
pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
bno = be64_to_cpu(*pp);
if (unlikely((error =
xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
xfs_trans_brelse(tp, bp);
XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
xfs_trans_brelse(tp, bp);
} else {
/* count all level 1 nodes and their leaves */
for (;;) {
nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
numrecs = be16_to_cpu(block->bb_numrecs);
xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
xfs_trans_brelse(tp, bp);
if (nextbno == NULLFSBLOCK)
break;
bno = nextbno;
error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
*count += 1;
block = XFS_BUF_TO_BLOCK(bp);
}
}
return 0;
}
/*
* Count fsblocks of the given fork.
*/
int /* error */
xfs_bmap_count_blocks(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode */
int whichfork, /* data or attr fork */
int *count) /* out: count of blocks */
{
struct xfs_btree_block *block; /* current btree block */
xfs_fsblock_t bno; /* block # of "block" */
xfs_ifork_t *ifp; /* fork structure */
int level; /* btree level, for checking */
xfs_mount_t *mp; /* file system mount structure */
__be64 *pp; /* pointer to block address */
bno = NULLFSBLOCK;
mp = ip->i_mount;
ifp = XFS_IFORK_PTR(ip, whichfork);
if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
xfs_bmap_count_leaves(ifp, 0,
ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
count);
return 0;
}
/*
* Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
*/
block = ifp->if_broot;
level = be16_to_cpu(block->bb_level);
ASSERT(level > 0);
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
bno = be64_to_cpu(*pp);
ASSERT(bno != NULLDFSBNO);
ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
/*
* Debug/sanity checking code
*/
@@ -824,7 +645,7 @@ xfs_bmap_add_free(
* Remove the entry "free" from the free item list. Prev points to the
* previous entry, unless "free" is the head of the list.
*/
STATIC void
void
xfs_bmap_del_free(
xfs_bmap_free_t *flist, /* free item list header */
xfs_bmap_free_item_t *prev, /* previous item on list, if any */
@@ -838,92 +659,6 @@ xfs_bmap_del_free(
kmem_zone_free(xfs_bmap_free_item_zone, free);
}
/*
* Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
* caller. Frees all the extents that need freeing, which must be done
* last due to locking considerations. We never free any extents in
* the first transaction.
*
* Return 1 if the given transaction was committed and a new one
* started, and 0 otherwise in the committed parameter.
*/
int /* error */
xfs_bmap_finish(
xfs_trans_t **tp, /* transaction pointer addr */
xfs_bmap_free_t *flist, /* i/o: list extents to free */
int *committed) /* xact committed or not */
{
xfs_efd_log_item_t *efd; /* extent free data */
xfs_efi_log_item_t *efi; /* extent free intention */
int error; /* error return value */
xfs_bmap_free_item_t *free; /* free extent item */
unsigned int logres; /* new log reservation */
unsigned int logcount; /* new log count */
xfs_mount_t *mp; /* filesystem mount structure */
xfs_bmap_free_item_t *next; /* next item on free list */
xfs_trans_t *ntp; /* new transaction pointer */
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
if (flist->xbf_count == 0) {
*committed = 0;
return 0;
}
ntp = *tp;
efi = xfs_trans_get_efi(ntp, flist->xbf_count);
for (free = flist->xbf_first; free; free = free->xbfi_next)
xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
free->xbfi_blockcount);
logres = ntp->t_log_res;
logcount = ntp->t_log_count;
ntp = xfs_trans_dup(*tp);
error = xfs_trans_commit(*tp, 0);
*tp = ntp;
*committed = 1;
/*
* We have a new transaction, so we should return committed=1,
* even though we're returning an error.
*/
if (error)
return error;
/*
* transaction commit worked ok so we can drop the extra ticket
* reference that we gained in xfs_trans_dup()
*/
xfs_log_ticket_put(ntp->t_ticket);
if ((error = xfs_trans_reserve(ntp, 0, logres, 0, XFS_TRANS_PERM_LOG_RES,
logcount)))
return error;
efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
for (free = flist->xbf_first; free != NULL; free = next) {
next = free->xbfi_next;
if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
free->xbfi_blockcount))) {
/*
* The bmap free list will be cleaned up at a
* higher level. The EFI will be canceled when
* this transaction is aborted.
* Need to force shutdown here to make sure it
* happens, since this transaction may not be
* dirty yet.
*/
mp = ntp->t_mountp;
if (!XFS_FORCED_SHUTDOWN(mp))
xfs_force_shutdown(mp,
(error == EFSCORRUPTED) ?
SHUTDOWN_CORRUPT_INCORE :
SHUTDOWN_META_IO_ERROR);
return error;
}
xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
free->xbfi_blockcount);
xfs_bmap_del_free(flist, NULL, free);
}
return 0;
}
/*
* Free up any items left in the list.
*/
@@ -1864,7 +1599,7 @@ xfs_bmap_last_before(
return 0;
}
STATIC int
int
xfs_bmap_last_extent(
struct xfs_trans *tp,
struct xfs_inode *ip,
@@ -1927,29 +1662,6 @@ xfs_bmap_isaeof(
return 0;
}
/*
* Check if the endoff is outside the last extent. If so the caller will grow
* the allocation to a stripe unit boundary. All offsets are considered outside
* the end of file for an empty fork, so 1 is returned in *eof in that case.
*/
int
xfs_bmap_eof(
struct xfs_inode *ip,
xfs_fileoff_t endoff,
int whichfork,
int *eof)
{
struct xfs_bmbt_irec rec;
int error;
error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
if (error || *eof)
return error;
*eof = endoff >= rec.br_startoff + rec.br_blockcount;
return 0;
}
/*
* Returns the file-relative block number of the first block past eof in
* the file. This is not based on i_size, it is based on the extent records.
@@ -3489,7 +3201,7 @@ done:
/*
* Adjust the size of the new extent based on di_extsize and rt extsize.
*/
STATIC int
int
xfs_bmap_extsize_align(
xfs_mount_t *mp,
xfs_bmbt_irec_t *gotp, /* next extent pointer */
@@ -3651,9 +3363,9 @@ xfs_bmap_extsize_align(
#define XFS_ALLOC_GAP_UNITS 4
STATIC void
void
xfs_bmap_adjacent(
xfs_bmalloca_t *ap) /* bmap alloc argument struct */
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
xfs_fsblock_t adjust; /* adjustment to block numbers */
xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */
@@ -3799,109 +3511,6 @@ xfs_bmap_adjacent(
#undef ISVALID
}
STATIC int
xfs_bmap_rtalloc(
xfs_bmalloca_t *ap) /* bmap alloc argument struct */
{
xfs_alloctype_t atype = 0; /* type for allocation routines */
int error; /* error return value */
xfs_mount_t *mp; /* mount point structure */
xfs_extlen_t prod = 0; /* product factor for allocators */
xfs_extlen_t ralen = 0; /* realtime allocation length */
xfs_extlen_t align; /* minimum allocation alignment */
xfs_rtblock_t rtb;
mp = ap->ip->i_mount;
align = xfs_get_extsz_hint(ap->ip);
prod = align / mp->m_sb.sb_rextsize;
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
align, 1, ap->eof, 0,
ap->conv, &ap->offset, &ap->length);
if (error)
return error;
ASSERT(ap->length);
ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);
/*
* If the offset & length are not perfectly aligned
* then kill prod, it will just get us in trouble.
*/
if (do_mod(ap->offset, align) || ap->length % align)
prod = 1;
/*
* Set ralen to be the actual requested length in rtextents.
*/
ralen = ap->length / mp->m_sb.sb_rextsize;
/*
* If the old value was close enough to MAXEXTLEN that
* we rounded up to it, cut it back so it's valid again.
* Note that if it's a really large request (bigger than
* MAXEXTLEN), we don't hear about that number, and can't
* adjust the starting point to match it.
*/
if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
/*
* Lock out other modifications to the RT bitmap inode.
*/
xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
/*
* If it's an allocation to an empty file at offset 0,
* pick an extent that will space things out in the rt area.
*/
if (ap->eof && ap->offset == 0) {
xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */
error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
if (error)
return error;
ap->blkno = rtx * mp->m_sb.sb_rextsize;
} else {
ap->blkno = 0;
}
xfs_bmap_adjacent(ap);
/*
* Realtime allocation, done through xfs_rtallocate_extent.
*/
atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
do_div(ap->blkno, mp->m_sb.sb_rextsize);
rtb = ap->blkno;
ap->length = ralen;
if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
&ralen, atype, ap->wasdel, prod, &rtb)))
return error;
if (rtb == NULLFSBLOCK && prod > 1 &&
(error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
ap->length, &ralen, atype,
ap->wasdel, 1, &rtb)))
return error;
ap->blkno = rtb;
if (ap->blkno != NULLFSBLOCK) {
ap->blkno *= mp->m_sb.sb_rextsize;
ralen *= mp->m_sb.sb_rextsize;
ap->length = ralen;
ap->ip->i_d.di_nblocks += ralen;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel)
ap->ip->i_delayed_blks -= ralen;
/*
* Adjust the disk quota also. This was reserved
* earlier.
*/
xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
} else {
ap->length = 0;
}
return 0;
}
STATIC int
xfs_bmap_btalloc_nullfb(
struct xfs_bmalloca *ap,
@@ -4019,7 +3628,7 @@ xfs_bmap_btalloc_nullfb(
STATIC int
xfs_bmap_btalloc(
xfs_bmalloca_t *ap) /* bmap alloc argument struct */
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
xfs_mount_t *mp; /* mount point structure */
xfs_alloctype_t atype = 0; /* type for allocation routines */
@@ -4251,7 +3860,7 @@ xfs_bmap_btalloc(
*/
STATIC int
xfs_bmap_alloc(
xfs_bmalloca_t *ap) /* bmap alloc argument struct */
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
if (XFS_IS_REALTIME_INODE(ap->ip) && ap->userdata)
return xfs_bmap_rtalloc(ap);
@@ -4639,7 +4248,7 @@ xfs_bmapi_delay(
}
STATIC int
int
__xfs_bmapi_allocate(
struct xfs_bmalloca *bma)
{
@@ -4757,45 +4366,6 @@ __xfs_bmapi_allocate(
return 0;
}
static void
xfs_bmapi_allocate_worker(
struct work_struct *work)
{
struct xfs_bmalloca *args = container_of(work,
struct xfs_bmalloca, work);
unsigned long pflags;
/* we are in a transaction context here */
current_set_flags_nested(&pflags, PF_FSTRANS);
args->result = __xfs_bmapi_allocate(args);
complete(args->done);
current_restore_flags_nested(&pflags, PF_FSTRANS);
}
/*
* Some allocation requests often come in with little stack to work on. Push
* them off to a worker thread so there is lots of stack to use. Otherwise just
* call directly to avoid the context switch overhead here.
*/
int
xfs_bmapi_allocate(
struct xfs_bmalloca *args)
{
DECLARE_COMPLETION_ONSTACK(done);
if (!args->stack_switch)
return __xfs_bmapi_allocate(args);
args->done = &done;
INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
queue_work(xfs_alloc_wq, &args->work);
wait_for_completion(&done);
return args->result;
}
STATIC int
xfs_bmapi_convert_unwritten(
struct xfs_bmalloca *bma,
@@ -5790,359 +5360,3 @@ error0:
}
return error;
}
/*
* returns 1 for success, 0 if we failed to map the extent.
*/
STATIC int
xfs_getbmapx_fix_eof_hole(
xfs_inode_t *ip, /* xfs incore inode pointer */
struct getbmapx *out, /* output structure */
int prealloced, /* this is a file with
* preallocated data space */
__int64_t end, /* last block requested */
xfs_fsblock_t startblock)
{
__int64_t fixlen;
xfs_mount_t *mp; /* file system mount point */
xfs_ifork_t *ifp; /* inode fork pointer */
xfs_extnum_t lastx; /* last extent pointer */
xfs_fileoff_t fileblock;
if (startblock == HOLESTARTBLOCK) {
mp = ip->i_mount;
out->bmv_block = -1;
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
fixlen -= out->bmv_offset;
if (prealloced && out->bmv_offset + out->bmv_length == end) {
/* Came to hole at EOF. Trim it. */
if (fixlen <= 0)
return 0;
out->bmv_length = fixlen;
}
} else {
if (startblock == DELAYSTARTBLOCK)
out->bmv_block = -2;
else
out->bmv_block = xfs_fsb_to_db(ip, startblock);
fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
(lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
out->bmv_oflags |= BMV_OF_LAST;
}
return 1;
}
/*
* Get inode's extents as described in bmv, and format for output.
* Calls formatter to fill the user's buffer until all extents
* are mapped, until the passed-in bmv->bmv_count slots have
* been filled, or until the formatter short-circuits the loop,
* if it is tracking filled-in extents on its own.
*/
int /* error code */
xfs_getbmap(
xfs_inode_t *ip,
struct getbmapx *bmv, /* user bmap structure */
xfs_bmap_format_t formatter, /* format to user */
void *arg) /* formatter arg */
{
__int64_t bmvend; /* last block requested */
int error = 0; /* return value */
__int64_t fixlen; /* length for -1 case */
int i; /* extent number */
int lock; /* lock state */
xfs_bmbt_irec_t *map; /* buffer for user's data */
xfs_mount_t *mp; /* file system mount point */
int nex; /* # of user extents can do */
int nexleft; /* # of user extents left */
int subnex; /* # of bmapi's can do */
int nmap; /* number of map entries */
struct getbmapx *out; /* output structure */
int whichfork; /* data or attr fork */
int prealloced; /* this is a file with
* preallocated data space */
int iflags; /* interface flags */
int bmapi_flags; /* flags for xfs_bmapi */
int cur_ext = 0;
mp = ip->i_mount;
iflags = bmv->bmv_iflags;
whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
if (whichfork == XFS_ATTR_FORK) {
if (XFS_IFORK_Q(ip)) {
if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
} else if (unlikely(
ip->i_d.di_aformat != 0 &&
ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
prealloced = 0;
fixlen = 1LL << 32;
} else {
if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
if (xfs_get_extsz_hint(ip) ||
ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
prealloced = 1;
fixlen = mp->m_super->s_maxbytes;
} else {
prealloced = 0;
fixlen = XFS_ISIZE(ip);
}
}
if (bmv->bmv_length == -1) {
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
bmv->bmv_length =
max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
} else if (bmv->bmv_length == 0) {
bmv->bmv_entries = 0;
return 0;
} else if (bmv->bmv_length < 0) {
return XFS_ERROR(EINVAL);
}
nex = bmv->bmv_count - 1;
if (nex <= 0)
return XFS_ERROR(EINVAL);
bmvend = bmv->bmv_offset + bmv->bmv_length;
if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
return XFS_ERROR(ENOMEM);
out = kmem_zalloc(bmv->bmv_count * sizeof(struct getbmapx), KM_MAYFAIL);
if (!out) {
out = kmem_zalloc_large(bmv->bmv_count *
sizeof(struct getbmapx));
if (!out)
return XFS_ERROR(ENOMEM);
}
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) {
error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
}
/*
* even after flushing the inode, there can still be delalloc
* blocks on the inode beyond EOF due to speculative
* preallocation. These are not removed until the release
* function is called or the inode is inactivated. Hence we
* cannot assert here that ip->i_delayed_blks == 0.
*/
}
lock = xfs_ilock_map_shared(ip);
/*
* Don't let nex be bigger than the number of extents
* we can have assuming alternating holes and real extents.
*/
if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
bmapi_flags = xfs_bmapi_aflag(whichfork);
if (!(iflags & BMV_IF_PREALLOC))
bmapi_flags |= XFS_BMAPI_IGSTATE;
/*
* Allocate enough space to handle "subnex" maps at a time.
*/
error = ENOMEM;
subnex = 16;
map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
if (!map)
goto out_unlock_ilock;
bmv->bmv_entries = 0;
if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
(whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
error = 0;
goto out_free_map;
}
nexleft = nex;
do {
nmap = (nexleft > subnex) ? subnex : nexleft;
error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
XFS_BB_TO_FSB(mp, bmv->bmv_length),
map, &nmap, bmapi_flags);
if (error)
goto out_free_map;
ASSERT(nmap <= subnex);
for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
out[cur_ext].bmv_oflags = 0;
if (map[i].br_state == XFS_EXT_UNWRITTEN)
out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
else if (map[i].br_startblock == DELAYSTARTBLOCK)
out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
out[cur_ext].bmv_offset =
XFS_FSB_TO_BB(mp, map[i].br_startoff);
out[cur_ext].bmv_length =
XFS_FSB_TO_BB(mp, map[i].br_blockcount);
out[cur_ext].bmv_unused1 = 0;
out[cur_ext].bmv_unused2 = 0;
/*
* delayed allocation extents that start beyond EOF can
* occur due to speculative EOF allocation when the
* delalloc extent is larger than the largest freespace
* extent at conversion time. These extents cannot be
* converted by data writeback, so can exist here even
* if we are not supposed to be finding delalloc
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
whichfork == XFS_ATTR_FORK) {
/* came to the end of attribute fork */
out[cur_ext].bmv_oflags |= BMV_OF_LAST;
goto out_free_map;
}
if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
prealloced, bmvend,
map[i].br_startblock))
goto out_free_map;
bmv->bmv_offset =
out[cur_ext].bmv_offset +
out[cur_ext].bmv_length;
bmv->bmv_length =
max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
/*
* In case we don't want to return the hole,
* don't increase cur_ext so that we can reuse
* it in the next loop.
*/
if ((iflags & BMV_IF_NO_HOLES) &&
map[i].br_startblock == HOLESTARTBLOCK) {
memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
continue;
}
nexleft--;
bmv->bmv_entries++;
cur_ext++;
}
} while (nmap && nexleft && bmv->bmv_length);
out_free_map:
kmem_free(map);
out_unlock_ilock:
xfs_iunlock_map_shared(ip, lock);
out_unlock_iolock:
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
for (i = 0; i < cur_ext; i++) {
int full = 0; /* user array is full */
/* format results & advance arg */
error = formatter(&arg, &out[i], &full);
if (error || full)
break;
}
if (is_vmalloc_addr(out))
kmem_free_large(out);
else
kmem_free(out);
return error;
}
/*
* dead simple method of punching delalyed allocation blocks from a range in
* the inode. Walks a block at a time so will be slow, but is only executed in
* rare error cases so the overhead is not critical. This will alays punch out
* both the start and end blocks, even if the ranges only partially overlap
* them, so it is up to the caller to ensure that partial blocks are not
* passed in.
*/
int
xfs_bmap_punch_delalloc_range(
struct xfs_inode *ip,
xfs_fileoff_t start_fsb,
xfs_fileoff_t length)
{
xfs_fileoff_t remaining = length;
int error = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
do {
int done;
xfs_bmbt_irec_t imap;
int nimaps = 1;
xfs_fsblock_t firstblock;
xfs_bmap_free_t flist;
/*
* Map the range first and check that it is a delalloc extent
* before trying to unmap the range. Otherwise we will be
* trying to remove a real extent (which requires a
* transaction) or a hole, which is probably a bad idea...
*/
error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
XFS_BMAPI_ENTIRE);
if (error) {
/* something screwed, just bail */
if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_alert(ip->i_mount,
"Failed delalloc mapping lookup ino %lld fsb %lld.",
ip->i_ino, start_fsb);
}
break;
}
if (!nimaps) {
/* nothing there */
goto next_block;
}
if (imap.br_startblock != DELAYSTARTBLOCK) {
/* been converted, ignore */
goto next_block;
}
WARN_ON(imap.br_blockcount == 0);
/*
* Note: while we initialise the firstblock/flist pair, they
* should never be used because blocks should never be
* allocated or freed for a delalloc extent and hence we need
* don't cancel or finish them after the xfs_bunmapi() call.
*/
xfs_bmap_init(&flist, &firstblock);
error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
&flist, &done);
if (error)
break;
ASSERT(!flist.xbf_count && !flist.xbf_first);
next_block:
start_fsb++;
remaining--;
} while(remaining > 0);
return error;
}