korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-15 08:14:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'xfs-4.10-misc-fixes-2' into iomap-4.10-directio

Browse Source
This commit is contained in:
Dave Chinner 2016-11-30 12:49:38 +11:00
commit e3df41f978
30 changed files with 965 additions and 1068 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
fs/iomap.c
View File

@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
struct page *page = data;
int ret;
ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
NULL, iomap);
ret = __block_write_begin_int(page, pos, length, NULL, iomap);
if (ret)
return ret;
@ -562,7 +561,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
}
while (len > 0) {
ret = iomap_apply(inode, start, len, 0, ops, &ctx,
ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
iomap_fiemap_actor);
/* inode with no (attribute) mapping will give ENOENT */
if (ret == -ENOENT)

731
fs/xfs/libxfs/xfs_bmap.c
View File

File diff suppressed because it is too large Load Diff

17
fs/xfs/libxfs/xfs_bmap.h
View File

@ -190,6 +190,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
#define XFS_BMAP_TRACE_EXLIST(ip,c,w)
#endif
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@ -221,7 +223,11 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, int flags,
xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops, int *done);
int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
struct xfs_bmbt_irec *del);
void xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
xfs_extnum_t num);
uint xfs_default_attroffset(struct xfs_inode *ip);
@ -231,14 +237,9 @@ int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
struct xfs_defer_ops *dfops, enum shift_direction direction,
int num_exts);
int xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
struct xfs_bmbt_rec_host *
xfs_bmap_search_extents(struct xfs_inode *ip, xfs_fileoff_t bno,
int fork, int *eofp, xfs_extnum_t *lastxp,
struct xfs_bmbt_irec *gotp, struct xfs_bmbt_irec *prevp);
int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
xfs_fileoff_t aoff, xfs_filblks_t len,
struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *prev,
xfs_extnum_t *lastx, int eof);
xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof);
enum xfs_bmap_intent_type {
XFS_BMAP_MAP = 1,

2
fs/xfs/libxfs/xfs_btree.c
View File

@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
return rval;
}
int
static int
xfs_btree_count_blocks_helper(
struct xfs_btree_cur *cur,
int level,

17
fs/xfs/libxfs/xfs_defer.c
View File

@ -199,9 +199,9 @@ xfs_defer_intake_work(
struct xfs_defer_pending *dfp;
list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
trace_xfs_defer_intake_work(tp->t_mountp, dfp);
dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
dfp->dfp_count);
trace_xfs_defer_intake_work(tp->t_mountp, dfp);
list_sort(tp->t_mountp, &dfp->dfp_work,
dfp->dfp_type->diff_items);
list_for_each(li, &dfp->dfp_work)
@ -221,21 +221,14 @@ xfs_defer_trans_abort(
struct xfs_defer_pending *dfp;
trace_xfs_defer_trans_abort(tp->t_mountp, dop);
/*
* If the transaction was committed, drop the intent reference
* since we're bailing out of here. The other reference is
* dropped when the intent hits the AIL. If the transaction
* was not committed, the intent is freed by the intent item
* unlock handler on abort.
*/
if (!dop->dop_committed)
return;
/* Abort intent items. */
/* Abort intent items that don't have a done item. */
list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
if (!dfp->dfp_done)
if (dfp->dfp_intent && !dfp->dfp_done) {
dfp->dfp_type->abort_intent(dfp->dfp_intent);
dfp->dfp_intent = NULL;
}
}
/* Shut down FS. */

2
fs/xfs/libxfs/xfs_dir2.c
View File

@ -93,7 +93,7 @@ xfs_ascii_ci_compname(
return result;
}
static struct xfs_nameops xfs_ascii_ci_nameops = {
static const struct xfs_nameops xfs_ascii_ci_nameops = {
.hashname = xfs_ascii_ci_hashname,
.compname = xfs_ascii_ci_compname,
};

3
fs/xfs/libxfs/xfs_dquot_buf.c
View File

@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
if (mp->m_quotainfo)
ndquots = mp->m_quotainfo->qi_dqperchunk;
else
ndquots = xfs_calc_dquots_per_chunk(
XFS_BB_TO_FSB(mp, bp->b_length));
ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
for (i = 0; i < ndquots; i++, d++) {
if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),

1
fs/xfs/libxfs/xfs_format.h
View File

@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
* padding field for v3 inodes.
*/
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3)
typedef struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__be16 di_mode; /* mode and type of file */

13
fs/xfs/libxfs/xfs_inode_buf.c
View File

@ -57,6 +57,17 @@ xfs_inobp_check(
}
#endif
bool
xfs_dinode_good_version(
struct xfs_mount *mp,
__u8 version)
{
if (xfs_sb_version_hascrc(&mp->m_sb))
return version == 3;
return version == 1 || version == 2;
}
/*
* If we are doing readahead on an inode buffer, we might be in log recovery
* reading an inode allocation buffer that hasn't yet been replayed, and hence
@ -91,7 +102,7 @@ xfs_inode_buf_verify(
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
XFS_DINODE_GOOD_VERSION(dip->di_version);
xfs_dinode_good_version(mp, dip->di_version);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP,
XFS_RANDOM_ITOBP_INOTOBP))) {

2
fs/xfs/libxfs/xfs_inode_buf.h
View File

@ -74,6 +74,8 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
void xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
struct xfs_dinode *to);
bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
#if defined(DEBUG)
void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#else

77
fs/xfs/libxfs/xfs_inode_fork.c
View File

@ -775,6 +775,13 @@ xfs_idestroy_fork(
}
}
/* Count number of incore extents based on if_bytes */
xfs_extnum_t
xfs_iext_count(struct xfs_ifork *ifp)
{
return ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
}
/*
* Convert in-core extents to on-disk form
*
@ -803,7 +810,7 @@ xfs_iextents_copy(
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(ifp->if_bytes > 0);
nrecs = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nrecs = xfs_iext_count(ifp);
XFS_BMAP_TRACE_EXLIST(ip, nrecs, whichfork);
ASSERT(nrecs > 0);
@ -941,7 +948,7 @@ xfs_iext_get_ext(
xfs_extnum_t idx) /* index of target extent */
{
ASSERT(idx >= 0);
ASSERT(idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t));
ASSERT(idx < xfs_iext_count(ifp));
if ((ifp->if_flags & XFS_IFEXTIREC) && (idx == 0)) {
return ifp->if_u1.if_ext_irec->er_extbuf;
@ -1017,7 +1024,7 @@ xfs_iext_add(
int new_size; /* size of extents after adding */
xfs_extnum_t nextents; /* number of extents in file */
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
ASSERT((idx >= 0) && (idx <= nextents));
byte_diff = ext_diff * sizeof(xfs_bmbt_rec_t);
new_size = ifp->if_bytes + byte_diff;
@ -1241,7 +1248,7 @@ xfs_iext_remove(
trace_xfs_iext_remove(ip, idx, state, _RET_IP_);
ASSERT(ext_diff > 0);
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
new_size = (nextents - ext_diff) * sizeof(xfs_bmbt_rec_t);
if (new_size == 0) {
@ -1270,7 +1277,7 @@ xfs_iext_remove_inline(
ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
ASSERT(idx < XFS_INLINE_EXTS);
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
ASSERT(((nextents - ext_diff) > 0) &&
(nextents - ext_diff) < XFS_INLINE_EXTS);
@ -1309,7 +1316,7 @@ xfs_iext_remove_direct(
ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
new_size = ifp->if_bytes -
(ext_diff * sizeof(xfs_bmbt_rec_t));
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
if (new_size == 0) {
xfs_iext_destroy(ifp);
@ -1546,7 +1553,7 @@ xfs_iext_indirect_to_direct(
int size; /* size of file extents */
ASSERT(ifp->if_flags & XFS_IFEXTIREC);
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
ASSERT(nextents <= XFS_LINEAR_EXTS);
size = nextents * sizeof(xfs_bmbt_rec_t);
@ -1620,7 +1627,7 @@ xfs_iext_bno_to_ext(
xfs_extnum_t nextents; /* number of file extents */
xfs_fileoff_t startoff = 0; /* start offset of extent */
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
if (nextents == 0) {
*idxp = 0;
return NULL;
@ -1733,8 +1740,8 @@ xfs_iext_idx_to_irec(
ASSERT(ifp->if_flags & XFS_IFEXTIREC);
ASSERT(page_idx >= 0);
ASSERT(page_idx <= ifp->if_bytes / sizeof(xfs_bmbt_rec_t));
ASSERT(page_idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t) || realloc);
ASSERT(page_idx <= xfs_iext_count(ifp));
ASSERT(page_idx < xfs_iext_count(ifp) || realloc);
nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
erp_idx = 0;
@ -1782,7 +1789,7 @@ xfs_iext_irec_init(
xfs_extnum_t nextents; /* number of extents in file */
ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
ASSERT(nextents <= XFS_LINEAR_EXTS);
erp = kmem_alloc(sizeof(xfs_ext_irec_t), KM_NOFS);
@ -1906,7 +1913,7 @@ xfs_iext_irec_compact(
ASSERT(ifp->if_flags & XFS_IFEXTIREC);
nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
if (nextents == 0) {
xfs_iext_destroy(ifp);
@ -1996,3 +2003,49 @@ xfs_ifork_init_cow(
ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
ip->i_cnextents = 0;
}
/*
* Lookup the extent covering bno.
*
* If there is an extent covering bno return the extent index, and store the
* expanded extent structure in *gotp, and the extent index in *idx.
* If there is no extent covering bno, but there is an extent after it (e.g.
* it lies in a hole) return that extent in *gotp and its index in *idx
* instead.
* If bno is beyond the last extent return false, and return the index after
* the last valid index in *idxp.
*/
bool
xfs_iext_lookup_extent(
struct xfs_inode *ip,
struct xfs_ifork *ifp,
xfs_fileoff_t bno,
xfs_extnum_t *idxp,
struct xfs_bmbt_irec *gotp)
{
struct xfs_bmbt_rec_host *ep;
XFS_STATS_INC(ip->i_mount, xs_look_exlist);
ep = xfs_iext_bno_to_ext(ifp, bno, idxp);
if (!ep)
return false;
xfs_bmbt_get_all(ep, gotp);
return true;
}
/*
* Return true if there is an extent at index idx, and return the expanded
* extent structure at idx in that case. Else return false.
*/
bool
xfs_iext_get_extent(
struct xfs_ifork *ifp,
xfs_extnum_t idx,
struct xfs_bmbt_irec *gotp)
{
if (idx < 0 || idx >= xfs_iext_count(ifp))
return false;
xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), gotp);
return true;
}

7
fs/xfs/libxfs/xfs_inode_fork.h
View File

@ -152,6 +152,7 @@ void xfs_init_local_fork(struct xfs_inode *, int, const void *, int);
struct xfs_bmbt_rec_host *
xfs_iext_get_ext(struct xfs_ifork *, xfs_extnum_t);
xfs_extnum_t xfs_iext_count(struct xfs_ifork *);
void xfs_iext_insert(struct xfs_inode *, xfs_extnum_t, xfs_extnum_t,
struct xfs_bmbt_irec *, int);
void xfs_iext_add(struct xfs_ifork *, xfs_extnum_t, int);
@ -181,6 +182,12 @@ void xfs_iext_irec_compact_pages(struct xfs_ifork *);
void xfs_iext_irec_compact_full(struct xfs_ifork *);
void xfs_iext_irec_update_extoffs(struct xfs_ifork *, int, int);
bool xfs_iext_lookup_extent(struct xfs_inode *ip,
struct xfs_ifork *ifp, xfs_fileoff_t bno,
xfs_extnum_t *idxp, struct xfs_bmbt_irec *gotp);
bool xfs_iext_get_extent(struct xfs_ifork *ifp, xfs_extnum_t idx,
struct xfs_bmbt_irec *gotp);
extern struct kmem_zone *xfs_ifork_zone;
extern void xfs_ifork_init_cow(struct xfs_inode *ip);

1
fs/xfs/libxfs/xfs_types.h
View File

@ -57,7 +57,6 @@ typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */
#define NULLAGBLOCK ((xfs_agblock_t)-1)
#define NULLAGNUMBER ((xfs_agnumber_t)-1)
#define NULLEXTNUM ((xfs_extnum_t)-1)
#define NULLCOMMITLSN ((xfs_lsn_t)-1)

38
fs/xfs/xfs_aops.c
View File

@ -777,7 +777,7 @@ xfs_map_cow(
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_bmbt_irec imap;
bool is_cow = false, need_alloc = false;
bool is_cow = false;
int error;
/*
@ -795,7 +795,7 @@ xfs_map_cow(
* Else we need to check if there is a COW mapping at this offset.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap, &need_alloc);
is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!is_cow)
@ -805,7 +805,7 @@ xfs_map_cow(
* And if the COW mapping has a delayed extent here we need to
* allocate real space for it now.
*/
if (need_alloc) {
if (isnullstartblock(imap.br_startblock)) {
error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset,
&imap);
if (error)
@ -1311,7 +1311,6 @@ __xfs_get_blocks(
ssize_t size;
int new = 0;
bool is_cow = false;
bool need_alloc = false;
BUG_ON(create && !direct);
@ -1337,9 +1336,11 @@ __xfs_get_blocks(
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
if (create && direct && xfs_is_reflink_inode(ip))
is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap,
&need_alloc);
if (create && direct && xfs_is_reflink_inode(ip)) {
is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
ASSERT(!is_cow || !isnullstartblock(imap.br_startblock));
}
if (!is_cow) {
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
&imap, &nimaps, XFS_BMAPI_ENTIRE);
@ -1356,10 +1357,29 @@ __xfs_get_blocks(
xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb,
&imap);
}
ASSERT(!need_alloc);
if (error)
goto out_unlock;
/*
* The only time we can ever safely find delalloc blocks on direct I/O
* is a dio write to post-eof speculative preallocation. All other
* scenarios are indicative of a problem or misuse (such as mixing
* direct and mapped I/O).
*
* The file may be unmapped by the time we get here so we cannot
* reliably fail the I/O based on mapping. Instead, fail the I/O if this
* is a read or a write within eof. Otherwise, carry on but warn as a
* precuation if the file happens to be mapped.
*/
if (direct && imap.br_startblock == DELAYSTARTBLOCK) {
if (!create || offset < i_size_read(VFS_I(ip))) {
WARN_ON_ONCE(1);
error = -EIO;
goto out_unlock;
}
WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping));
}
/* for DAX, we convert unwritten extents directly */
if (create &&
(!nimaps ||
@ -1444,8 +1464,6 @@ __xfs_get_blocks(
(new || ISUNWRITTEN(&imap))))
set_buffer_new(bh_result);
BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK);
return 0;
out_unlock:

33
fs/xfs/xfs_bmap_util.c
View File

@ -359,9 +359,7 @@ xfs_bmap_count_blocks(
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);
xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count);
return 0;
}
@ -426,7 +424,7 @@ xfs_getbmapx_fix_eof_hole(
ifp = XFS_IFORK_PTR(ip, whichfork);
if (!moretocome &&
xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
(lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
(lastx == xfs_iext_count(ifp) - 1))
out->bmv_oflags |= BMV_OF_LAST;
}
@ -1792,6 +1790,7 @@ xfs_swap_extent_forks(
struct xfs_ifork tempifp, *ifp, *tifp;
int aforkblks = 0;
int taforkblks = 0;
xfs_extnum_t nextents;
__uint64_t tmp;
int error;
@ -1877,14 +1876,13 @@ xfs_swap_extent_forks(
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
/*
* If the extents fit in the inode, fix the pointer. Otherwise
* it's already NULL or pointing to the extent.
*/
if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
ifp->if_u1.if_extents =
ifp->if_u2.if_inline_ext;
}
nextents = xfs_iext_count(&ip->i_df);
if (nextents <= XFS_INLINE_EXTS)
ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
(*src_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
@ -1896,14 +1894,13 @@ xfs_swap_extent_forks(
switch (tip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
/*
* If the extents fit in the inode, fix the pointer. Otherwise
* it's already NULL or pointing to the extent.
*/
if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
tifp->if_u1.if_extents =
tifp->if_u2.if_inline_ext;
}
nextents = xfs_iext_count(&tip->i_df);
if (nextents <= XFS_INLINE_EXTS)
tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext;
(*target_log_flags) |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:

1
fs/xfs/xfs_buf.h
View File

@ -71,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t;
{ XBF_READ, "READ" }, \
{ XBF_WRITE, "WRITE" }, \
{ XBF_READ_AHEAD, "READ_AHEAD" }, \
{ XBF_NO_IOACCT, "NO_IOACCT" }, \
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \

232
fs/xfs/xfs_file.c
View File

@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
struct xfs_inode *ip = XFS_I(inode);
loff_t isize = i_size_read(inode);
size_t count = iov_iter_count(to);
loff_t end = iocb->ki_pos + count - 1;
struct iov_iter data;
struct xfs_buftarg *target;
ssize_t ret = 0;
@ -272,49 +273,21 @@ xfs_file_dio_aio_read(
file_accessed(iocb->ki_filp);
/*
* Locking is a bit tricky here. If we take an exclusive lock for direct
* IO, we effectively serialise all new concurrent read IO to this file
* and block it behind IO that is currently in progress because IO in
* progress holds the IO lock shared. We only need to hold the lock
* exclusive to blow away the page cache, so only take lock exclusively
* if the page cache needs invalidation. This allows the normal direct
* IO case of no page cache pages to proceeed concurrently without
* serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if (mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
if (ret)
goto out_unlock;
/*
* The generic dio code only flushes the range of the particular
* I/O. Because we take an exclusive lock here, this whole
* sequence is considerably more expensive for us. This has a
* noticeable performance impact for any file with cached pages,
* even when outside of the range of the particular I/O.
*
* Hence, amortize the cost of the lock against a full file
* flush and reduce the chances of repeated iolock cycles going
* forward.
* Invalidate whole pages. This can return an error if we fail
* to invalidate a page, but this should never happen on XFS.
* Warn if it does fail.
*/
if (mapping->nrpages) {
ret = filemap_write_and_wait(mapping);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Invalidate whole pages. This can return an error if
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
ret = invalidate_inode_pages2(mapping);
WARN_ON_ONCE(ret);
ret = 0;
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
ret = invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
data = *to;
@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
iocb->ki_pos += ret;
iov_iter_advance(to, ret);
}
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
out_unlock:
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
@ -570,61 +544,49 @@ xfs_file_dio_aio_write(
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
/*
* Don't take the exclusive iolock here unless the I/O is unaligned to
* the file system block size. We don't need to consider the EOF
* extension case here because xfs_file_aio_write_checks() will relock
* the inode as necessary for EOF zeroing cases and fill out the new
* inode size as appropriate.
*/
if ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask))
((iocb->ki_pos + count) & mp->m_blockmask)) {
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
} else {
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
xfs_rw_ilock(ip, iolock);
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
end = iocb->ki_pos + count - 1;
/*
* See xfs_file_dio_aio_read() for why we do a full-file flush here.
*/
if (mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
if (ret)
goto out;
/*
* Invalidate whole pages. This can return an error if we fail
* to invalidate a page, but this should never happen on XFS.
* Warn if it does fail.
*/
ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
ret = invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
* otherwise demote the lock if we had to take the exclusive lock
* for other reasons in xfs_file_aio_write_checks.
*/
if (unaligned_io)
inode_dio_wait(inode);
@ -947,134 +909,6 @@ out_unlock:
return error;
}
/*
* Flush all file writes out to disk.
*/
static int
xfs_file_wait_for_io(
struct inode *inode,
loff_t offset,
size_t len)
{
loff_t rounding;
loff_t ioffset;
loff_t iendoffset;
loff_t bs;
int ret;
bs = inode->i_sb->s_blocksize;
inode_dio_wait(inode);
rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
ioffset = round_down(offset, rounding);
iendoffset = round_up(offset + len, rounding) - 1;
ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
iendoffset);
return ret;
}
/* Hook up to the VFS reflink function */
STATIC int
xfs_file_share_range(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
struct inode *inode_in;
struct inode *inode_out;
ssize_t ret;
loff_t bs;
loff_t isize;
int same_inode;
loff_t blen;
unsigned int flags = 0;
inode_in = file_inode(file_in);
inode_out = file_inode(file_out);
bs = inode_out->i_sb->s_blocksize;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) ||
IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Reflink only works within this filesystem. */
if (inode_in->i_sb != inode_out->i_sb)
return -EXDEV;
same_inode = (inode_in->i_ino == inode_out->i_ino);
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
return -EINVAL;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
return -EINVAL;
/* Are we going all the way to the end? */
isize = i_size_read(inode_in);
if (isize == 0)
return 0;
if (len == 0)
len = isize - pos_in;
/* Ensure offsets don't wrap and the input is inside i_size */
if (pos_in + len < pos_in || pos_out + len < pos_out ||
pos_in + len > isize)
return -EINVAL;
/* Don't allow dedupe past EOF in the dest file */
if (is_dedupe) {
loff_t disize;
disize = i_size_read(inode_out);
if (pos_out >= disize || pos_out + len > disize)
return -EINVAL;
}
/* If we're linking to EOF, continue to the block boundary. */
if (pos_in + len == isize)
blen = ALIGN(isize, bs) - pos_in;
else
blen = len;
/* Only reflink if we're aligned to block boundaries */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
!IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
return -EINVAL;
/* Don't allow overlapped reflink within the same file */
if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
return -EINVAL;
/* Wait for the completion of any pending IOs on srcfile */
ret = xfs_file_wait_for_io(inode_in, pos_in, len);
if (ret)
goto out;
ret = xfs_file_wait_for_io(inode_out, pos_out, len);
if (ret)
goto out;
if (is_dedupe)
flags |= XFS_REFLINK_DEDUPE;
ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
pos_out, len, flags);
if (ret < 0)
goto out;
out:
return ret;
}
STATIC ssize_t
xfs_file_copy_range(
struct file *file_in,
@ -1086,7 +920,7 @@ xfs_file_copy_range(
{
int error;
error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
len, false);
if (error)
return error;
@ -1101,7 +935,7 @@ xfs_file_clone_range(
loff_t pos_out,
u64 len)
{
return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
len, false);
}
@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
if (len > XFS_MAX_DEDUPE_LEN)
len = XFS_MAX_DEDUPE_LEN;
error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
len, true);
if (error)
return error;

42
fs/xfs/xfs_icache.c
View File

@ -123,7 +123,6 @@ __xfs_inode_free(
{
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!xfs_isiflocked(ip));
XFS_STATS_DEC(ip->i_mount, vn_active);
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
@ -133,6 +132,8 @@ void
xfs_inode_free(
struct xfs_inode *ip)
{
ASSERT(!xfs_isiflocked(ip));
/*
* Because we use RCU freeing we need to ensure the inode always
* appears to be reclaimed with an invalid inode number when in the
@ -981,6 +982,7 @@ restart:
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
/* xfs_iflush_abort() drops the flush lock */
xfs_iflush_abort(ip, false);
goto reclaim;
}
@ -989,10 +991,10 @@ restart:
goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
xfs_ifunlock(ip);
goto reclaim;
}
/*
* Never flush out dirty data during non-blocking reclaim, as it would
@ -1030,25 +1032,24 @@ restart:
xfs_buf_relse(bp);
}
xfs_iflock(ip);
reclaim:
ASSERT(!xfs_isiflocked(ip));
/*
* Because we use RCU freeing we need to ensure the inode always appears
* to be reclaimed with an invalid inode number when in the free state.
* We do this as early as possible under the ILOCK and flush lock so
* that xfs_iflush_cluster() can be guaranteed to detect races with us
* here. By doing this, we guarantee that once xfs_iflush_cluster has
* locked both the XFS_ILOCK and the flush lock that it will see either
* a valid, flushable inode that will serialise correctly against the
* locks below, or it will see a clean (and invalid) inode that it can
* skip.
* We do this as early as possible under the ILOCK so that
* xfs_iflush_cluster() can be guaranteed to detect races with us here.
* By doing this, we guarantee that once xfs_iflush_cluster has locked
* XFS_ILOCK that it will see either a valid, flushable inode that will
* serialise correctly, or it will see a clean (and invalid) inode that
* it can skip.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
@ -1580,10 +1581,15 @@ xfs_inode_free_cowblocks(
struct xfs_eofblocks *eofb = args;
bool need_iolock = true;
int match;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
if (!xfs_reflink_has_real_cow_blocks(ip)) {
/*
* Just clear the tag if we have an empty cow fork or none at all. It's
* possible the inode was fully unshared since it was originally tagged.
*/
if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
trace_xfs_inode_free_cowblocks_invalid(ip);
xfs_inode_clear_cowblocks_tag(ip);
return 0;
@ -1656,9 +1662,9 @@ void
xfs_inode_set_cowblocks_tag(
xfs_inode_t *ip)
{
trace_xfs_inode_set_eofblocks_tag(ip);
trace_xfs_inode_set_cowblocks_tag(ip);
return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
trace_xfs_perag_set_eofblocks,
trace_xfs_perag_set_cowblocks,
XFS_ICI_COWBLOCKS_TAG);
}
@ -1666,7 +1672,7 @@ void
xfs_inode_clear_cowblocks_tag(
xfs_inode_t *ip)
{
trace_xfs_inode_clear_eofblocks_tag(ip);
trace_xfs_inode_clear_cowblocks_tag(ip);
return __xfs_inode_clear_eofblocks_tag(ip,
trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
}

2
fs/xfs/xfs_icreate_item.c
View File

@ -133,7 +133,7 @@ xfs_icreate_item_committing(
/*
* This is the ops vector shared by all buf log items.
*/
static struct xfs_item_ops xfs_icreate_item_ops = {
static const struct xfs_item_ops xfs_icreate_item_ops = {
.iop_size = xfs_icreate_item_size,
.iop_format = xfs_icreate_item_format,
.iop_pin = xfs_icreate_item_pin,

11
fs/xfs/xfs_inode.h
View File

@ -246,6 +246,11 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
* Synchronize processes attempting to flush the in-core inode back to disk.
*/
static inline int xfs_isiflocked(struct xfs_inode *ip)
{
return xfs_iflags_test(ip, XFS_IFLOCK);
}
extern void __xfs_iflock(struct xfs_inode *ip);
static inline int xfs_iflock_nowait(struct xfs_inode *ip)
@ -261,16 +266,12 @@ static inline void xfs_iflock(struct xfs_inode *ip)
static inline void xfs_ifunlock(struct xfs_inode *ip)
{
ASSERT(xfs_isiflocked(ip));
xfs_iflags_clear(ip, XFS_IFLOCK);
smp_mb();
wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
}
static inline int xfs_isiflocked(struct xfs_inode *ip)
{
return xfs_iflags_test(ip, XFS_IFLOCK);
}
/*
* Flags for inode locking.
* Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield)

4
fs/xfs/xfs_inode_item.c
View File

@ -164,7 +164,7 @@ xfs_inode_item_format_data_fork(
struct xfs_bmbt_rec *p;
ASSERT(ip->i_df.if_u1.if_extents != NULL);
ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0);
ASSERT(xfs_iext_count(&ip->i_df) > 0);
p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT);
data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK);
@ -261,7 +261,7 @@ xfs_inode_item_format_attr_fork(
ip->i_afp->if_bytes > 0) {
struct xfs_bmbt_rec *p;
ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) ==
ASSERT(xfs_iext_count(ip->i_afp) ==
ip->i_d.di_anextents);
ASSERT(ip->i_afp->if_u1.if_extents != NULL);

6
fs/xfs/xfs_ioctl.c
View File

@ -910,16 +910,14 @@ xfs_ioc_fsgetxattr(
if (attr) {
if (ip->i_afp) {
if (ip->i_afp->if_flags & XFS_IFEXTENTS)
fa.fsx_nextents = ip->i_afp->if_bytes /
sizeof(xfs_bmbt_rec_t);
fa.fsx_nextents = xfs_iext_count(ip->i_afp);
else
fa.fsx_nextents = ip->i_d.di_anextents;
} else
fa.fsx_nextents = 0;
} else {
if (ip->i_df.if_flags & XFS_IFEXTENTS)
fa.fsx_nextents = ip->i_df.if_bytes /
sizeof(xfs_bmbt_rec_t);
fa.fsx_nextents = xfs_iext_count(&ip->i_df);
else
fa.fsx_nextents = ip->i_d.di_nextents;
}

111
fs/xfs/xfs_iomap.c
View File

@ -395,11 +395,12 @@ xfs_iomap_prealloc_size(
struct xfs_inode *ip,
loff_t offset,
loff_t count,
xfs_extnum_t idx,
struct xfs_bmbt_irec *prev)
xfs_extnum_t idx)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
struct xfs_bmbt_irec prev;
int shift = 0;
int64_t freesp;
xfs_fsblock_t qblocks;
@ -419,8 +420,8 @@ xfs_iomap_prealloc_size(
*/
if ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ||
XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) ||
idx == 0 ||
prev->br_startoff + prev->br_blockcount < offset_fsb)
!xfs_iext_get_extent(ifp, idx - 1, &prev) ||
prev.br_startoff + prev.br_blockcount < offset_fsb)
return mp->m_writeio_blocks;
/*
@ -439,8 +440,8 @@ xfs_iomap_prealloc_size(
* always extends to MAXEXTLEN rather than falling short due to things
* like stripe unit/width alignment of real extents.
*/
if (prev->br_blockcount <= (MAXEXTLEN >> 1))
alloc_blocks = prev->br_blockcount << 1;
if (prev.br_blockcount <= (MAXEXTLEN >> 1))
alloc_blocks = prev.br_blockcount << 1;
else
alloc_blocks = XFS_B_TO_FSB(mp, offset);
if (!alloc_blocks)
@ -535,11 +536,11 @@ xfs_file_iomap_begin_delay(
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t maxbytes_fsb =
XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
xfs_fileoff_t end_fsb, orig_end_fsb;
xfs_fileoff_t end_fsb;
int error = 0, eof = 0;
struct xfs_bmbt_irec got;
struct xfs_bmbt_irec prev;
xfs_extnum_t idx;
xfs_fsblock_t prealloc_blocks = 0;
ASSERT(!XFS_IS_REALTIME_INODE(ip));
ASSERT(!xfs_get_extsz_hint(ip));
@ -563,9 +564,19 @@ xfs_file_iomap_begin_delay(
goto out_unlock;
}
xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
&got, &prev);
eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
if (!eof && got.br_startoff <= offset_fsb) {
if (xfs_is_reflink_inode(ip)) {
bool shared;
end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
maxbytes_fsb);
xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
error = xfs_reflink_reserve_cow(ip, &got, &shared);
if (error)
goto out_unlock;
}
trace_xfs_iomap_found(ip, offset, count, 0, &got);
goto done;
}
@ -584,35 +595,32 @@ xfs_file_iomap_begin_delay(
* the lower level functions are updated.
*/
count = min_t(loff_t, count, 1024 * PAGE_SIZE);
end_fsb = orig_end_fsb =
min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);
end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);
if (eof) {
xfs_fsblock_t prealloc_blocks;
prealloc_blocks =
xfs_iomap_prealloc_size(ip, offset, count, idx, &prev);
prealloc_blocks = xfs_iomap_prealloc_size(ip, offset, count, idx);
if (prealloc_blocks) {
xfs_extlen_t align;
xfs_off_t end_offset;
xfs_fileoff_t p_end_fsb;
end_offset = XFS_WRITEIO_ALIGN(mp, offset + count - 1);
end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
prealloc_blocks;
p_end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
prealloc_blocks;
align = xfs_eof_alignment(ip, 0);
if (align)
end_fsb = roundup_64(end_fsb, align);
p_end_fsb = roundup_64(p_end_fsb, align);
end_fsb = min(end_fsb, maxbytes_fsb);
ASSERT(end_fsb > offset_fsb);
p_end_fsb = min(p_end_fsb, maxbytes_fsb);
ASSERT(p_end_fsb > offset_fsb);
prealloc_blocks = p_end_fsb - end_fsb;
}
}
retry:
error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb,
end_fsb - offset_fsb, &got,
&prev, &idx, eof);
end_fsb - offset_fsb, prealloc_blocks, &got, &idx, eof);
switch (error) {
case 0:
break;
@ -620,8 +628,8 @@ retry:
case -EDQUOT:
/* retry without any preallocation */
trace_xfs_delalloc_enospc(ip, offset, count);
if (end_fsb != orig_end_fsb) {
end_fsb = orig_end_fsb;
if (prealloc_blocks) {
prealloc_blocks = 0;
goto retry;
}
/*FALLTHRU*/
@ -629,13 +637,6 @@ retry:
goto out_unlock;
}
/*
* Tag the inode as speculatively preallocated so we can reclaim this
* space on demand, if necessary.
*/
if (end_fsb != orig_end_fsb)
xfs_inode_set_eofblocks_tag(ip);
trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
done:
if (isnullstartblock(got.br_startblock))
@ -961,19 +962,13 @@ xfs_file_iomap_begin(
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap;
xfs_fileoff_t offset_fsb, end_fsb;
bool shared, trimmed;
int nimaps = 1, error = 0;
bool shared = false, trimmed = false;
unsigned lockmode;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
error = xfs_reflink_reserve_cow_range(ip, offset, length);
if (error < 0)
return error;
}
if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
!xfs_get_extsz_hint(ip)) {
/* Reserve delalloc blocks for regular writeback. */
@ -981,7 +976,16 @@ xfs_file_iomap_begin(
iomap);
}
lockmode = xfs_ilock_data_map_shared(ip);
/*
* COW writes will allocate delalloc space, so we need to make sure
* to take the lock exclusively here.
*/
if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
} else {
lockmode = xfs_ilock_data_map_shared(ip);
}
ASSERT(offset <= mp->m_super->s_maxbytes);
if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@ -991,16 +995,24 @@ xfs_file_iomap_begin(
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, 0);
if (error) {
xfs_iunlock(ip, lockmode);
return error;
if (error)
goto out_unlock;
if (flags & IOMAP_REPORT) {
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
&trimmed);
if (error)
goto out_unlock;
}
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
if (error) {
xfs_iunlock(ip, lockmode);
return error;
if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
error = xfs_reflink_reserve_cow(ip, &imap, &shared);
if (error)
goto out_unlock;
end_fsb = imap.br_startoff + imap.br_blockcount;
length = XFS_FSB_TO_B(mp, end_fsb) - offset;
}
if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@ -1039,6 +1051,9 @@ xfs_file_iomap_begin(
if (shared)
iomap->flags |= IOMAP_F_SHARED;
return 0;
out_unlock:
xfs_iunlock(ip, lockmode);
return error;
}
static int

1
fs/xfs/xfs_mount.c
View File

@ -1009,6 +1009,7 @@ xfs_mountfs(
out_quota:
xfs_qm_unmount_quotas(mp);
out_rtunmount:
mp->m_super->s_flags &= ~MS_ACTIVE;
xfs_rtunmount_inodes(mp);
out_rele_rip:
IRELE(rip);

2
fs/xfs/xfs_qm.c
View File

@ -1135,7 +1135,7 @@ xfs_qm_get_rtblks(
return error;
}
rtblks = 0;
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
nextents = xfs_iext_count(ifp);
for (idx = 0; idx < nextents; idx++)
rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx));
*O_rtblks = (xfs_qcnt_t)rtblks;

630
fs/xfs/xfs_reflink.c
View File

@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared(
if (!xfs_is_reflink_inode(ip) ||
ISUNWRITTEN(irec) ||
irec->br_startblock == HOLESTARTBLOCK ||
irec->br_startblock == DELAYSTARTBLOCK) {
irec->br_startblock == DELAYSTARTBLOCK ||
isnullstartblock(irec->br_startblock)) {
*shared = false;
return 0;
}
@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared(
}
}
/* Create a CoW reservation for a range of blocks within a file. */
static int
__xfs_reflink_reserve_cow(
/*
* Trim the passed in imap to the next shared/unshared extent boundary, and
* if imap->br_startoff points to a shared extent reserve space for it in the
* COW fork. In this case *shared is set to true, else to false.
*
* Note that imap will always contain the block numbers for the existing blocks
* in the data fork, as the upper layers need them for read-modify-write
* operations.
*/
int
xfs_reflink_reserve_cow(
struct xfs_inode *ip,
xfs_fileoff_t *offset_fsb,
xfs_fileoff_t end_fsb,
bool *skipped)
struct xfs_bmbt_irec *imap,
bool *shared)
{
struct xfs_bmbt_irec got, prev, imap;
xfs_fileoff_t orig_end_fsb;
int nimaps, eof = 0, error = 0;
bool shared = false, trimmed = false;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got;
int error = 0;
bool eof = false, trimmed;
xfs_extnum_t idx;
xfs_extlen_t align;
/* Already reserved? Skip the refcount btree access. */
xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
&got, &prev);
if (!eof && got.br_startoff <= *offset_fsb) {
end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
trace_xfs_reflink_cow_found(ip, &got);
goto done;
/*
* Search the COW fork extent list first. This serves two purposes:
* first this implement the speculative preallocation using cowextisze,
* so that we also unshared block adjacent to shared blocks instead
* of just the shared blocks themselves. Second the lookup in the
* extent list is generally faster than going out to the shared extent
* tree.
*/
if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &idx, &got))
eof = true;
if (!eof && got.br_startoff <= imap->br_startoff) {
trace_xfs_reflink_cow_found(ip, imap);
xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
*shared = true;
return 0;
}
/* Read extent from the source file. */
nimaps = 1;
error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
&imap, &nimaps, 0);
if (error)
goto out_unlock;
ASSERT(nimaps == 1);
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
if (error)
goto out_unlock;
end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
return error;
/* Not shared? Just report the (potentially capped) extent. */
if (!shared) {
*skipped = true;
goto done;
}
if (!*shared)
return 0;
/*
* Fork all the shared blocks from our write offset until the end of
@ -278,72 +283,17 @@ __xfs_reflink_reserve_cow(
*/
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
return error;
align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip));
if (align)
end_fsb = roundup_64(end_fsb, align);
retry:
error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
end_fsb - *offset_fsb, &got,
&prev, &idx, eof);
switch (error) {
case 0:
break;
case -ENOSPC:
case -EDQUOT:
/* retry without any preallocation */
trace_xfs_reflink_cow_enospc(ip, &imap);
if (end_fsb != orig_end_fsb) {
end_fsb = orig_end_fsb;
goto retry;
}
/*FALLTHRU*/
default:
goto out_unlock;
}
if (end_fsb != orig_end_fsb)
xfs_inode_set_cowblocks_tag(ip);
error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
imap->br_blockcount, 0, &got, &idx, eof);
if (error == -ENOSPC || error == -EDQUOT)
trace_xfs_reflink_cow_enospc(ip, imap);
if (error)
return error;
trace_xfs_reflink_cow_alloc(ip, &got);
done:
*offset_fsb = end_fsb;
out_unlock:
return error;
}
/* Create a CoW reservation for part of a file. */
int
xfs_reflink_reserve_cow_range(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb, end_fsb;
bool skipped = false;
int error;
trace_xfs_reflink_reserve_cow_range(ip, offset, count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_ilock(ip, XFS_ILOCK_EXCL);
while (offset_fsb < end_fsb) {
error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb,
&skipped);
if (error) {
trace_xfs_reflink_reserve_cow_range_error(ip, error,
_RET_IP_);
break;
}
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
return 0;
}
/* Allocate all CoW reservations covering a range of blocks in a file. */
@ -358,9 +308,8 @@ __xfs_reflink_allocate_cow(
struct xfs_defer_ops dfops;
struct xfs_trans *tp;
xfs_fsblock_t first_block;
xfs_fileoff_t next_fsb;
int nimaps = 1, error;
bool skipped = false;
bool shared;
xfs_defer_init(&dfops, &first_block);
@ -371,33 +320,38 @@ __xfs_reflink_allocate_cow(
xfs_ilock(ip, XFS_ILOCK_EXCL);
next_fsb = *offset_fsb;
error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped);
/* Read extent from the source file. */
nimaps = 1;
error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
&imap, &nimaps, 0);
if (error)
goto out_unlock;
ASSERT(nimaps == 1);
error = xfs_reflink_reserve_cow(ip, &imap, &shared);
if (error)
goto out_trans_cancel;
if (skipped) {
*offset_fsb = next_fsb;
if (!shared) {
*offset_fsb = imap.br_startoff + imap.br_blockcount;
goto out_trans_cancel;
}
xfs_trans_ijoin(tp, ip, 0);
error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb,
error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
XFS_BMAPI_COWFORK, &first_block,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
&imap, &nimaps, &dfops);
if (error)
goto out_trans_cancel;
/* We might not have been able to map the whole delalloc extent */
*offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb);
error = xfs_defer_finish(&tp, &dfops, NULL);
if (error)
goto out_trans_cancel;
error = xfs_trans_commit(tp);
*offset_fsb = imap.br_startoff + imap.br_blockcount;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
@ -443,87 +397,65 @@ xfs_reflink_allocate_cow_range(
}
/*
* Find the CoW reservation (and whether or not it needs block allocation)
* for a given byte offset of a file.
* Find the CoW reservation for a given byte offset of a file.
*/
bool
xfs_reflink_find_cow_mapping(
struct xfs_inode *ip,
xfs_off_t offset,
struct xfs_bmbt_irec *imap,
bool *need_alloc)
struct xfs_bmbt_irec *imap)
{
struct xfs_bmbt_irec irec;
struct xfs_ifork *ifp;
struct xfs_bmbt_rec_host *gotp;
xfs_fileoff_t bno;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_fileoff_t offset_fsb;
struct xfs_bmbt_irec got;
xfs_extnum_t idx;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
ASSERT(xfs_is_reflink_inode(ip));
/* Find the extent in the CoW fork. */
ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
bno = XFS_B_TO_FSBT(ip->i_mount, offset);
gotp = xfs_iext_bno_to_ext(ifp, bno, &idx);
if (!gotp)
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return false;
xfs_bmbt_get_all(gotp, &irec);
if (bno >= irec.br_startoff + irec.br_blockcount ||
bno < irec.br_startoff)
if (got.br_startoff > offset_fsb)
return false;
trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
&irec);
/* If it's still delalloc, we must allocate later. */
*imap = irec;
*need_alloc = !!(isnullstartblock(irec.br_startblock));
&got);
*imap = got;
return true;
}
/*
* Trim an extent to end at the next CoW reservation past offset_fsb.
*/
int
void
xfs_reflink_trim_irec_to_next_cow(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
struct xfs_bmbt_irec *imap)
{
struct xfs_bmbt_irec irec;
struct xfs_ifork *ifp;
struct xfs_bmbt_rec_host *gotp;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got;
xfs_extnum_t idx;
if (!xfs_is_reflink_inode(ip))
return 0;
return;
/* Find the extent in the CoW fork. */
ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
gotp = xfs_iext_bno_to_ext(ifp, offset_fsb, &idx);
if (!gotp)
return 0;
xfs_bmbt_get_all(gotp, &irec);
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return;
/* This is the extent before; try sliding up one. */
if (irec.br_startoff < offset_fsb) {
idx++;
if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
return 0;
gotp = xfs_iext_get_ext(ifp, idx);
xfs_bmbt_get_all(gotp, &irec);
if (got.br_startoff < offset_fsb) {
if (!xfs_iext_get_extent(ifp, idx + 1, &got))
return;
}
if (irec.br_startoff >= imap->br_startoff + imap->br_blockcount)
return 0;
if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
return;
imap->br_blockcount = irec.br_startoff - imap->br_startoff;
imap->br_blockcount = got.br_startoff - imap->br_startoff;
trace_xfs_reflink_trim_irec(ip, imap);
return 0;
}
/*
@ -536,58 +468,46 @@ xfs_reflink_cancel_cow_blocks(
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb)
{
struct xfs_bmbt_irec irec;
xfs_filblks_t count_fsb;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
xfs_extnum_t idx;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error = 0;
int nimaps;
if (!xfs_is_reflink_inode(ip))
return 0;
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return 0;
/* Go find the old extent in the CoW fork. */
while (offset_fsb < end_fsb) {
nimaps = 1;
count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
&nimaps, XFS_BMAPI_COWFORK);
if (error)
break;
ASSERT(nimaps == 1);
while (got.br_startoff < end_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
trace_xfs_reflink_cancel_cow(ip, &del);
trace_xfs_reflink_cancel_cow(ip, &irec);
if (irec.br_startblock == DELAYSTARTBLOCK) {
/* Free a delayed allocation. */
xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount,
false);
ip->i_delayed_blks -= irec.br_blockcount;
/* Remove the mapping from the CoW fork. */
error = xfs_bunmapi_cow(ip, &irec);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&idx, &got, &del);
if (error)
break;
} else if (irec.br_startblock == HOLESTARTBLOCK) {
/* empty */
} else {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
&dfops, irec.br_startblock,
irec.br_blockcount);
&dfops, del.br_startblock,
del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
irec.br_startblock, irec.br_blockcount,
del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-(long)irec.br_blockcount);
-(long)del.br_blockcount);
/* Roll the transaction */
error = xfs_defer_finish(tpp, &dfops, ip);
@ -597,15 +517,17 @@ xfs_reflink_cancel_cow_blocks(
}
/* Remove the mapping from the CoW fork. */
error = xfs_bunmapi_cow(ip, &irec);
if (error)
break;
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
}
/* Roll on... */
offset_fsb = irec.br_startoff + irec.br_blockcount;
if (!xfs_iext_get_extent(ifp, ++idx, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
@ -668,25 +590,26 @@ xfs_reflink_end_cow(
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_bmbt_irec irec;
struct xfs_bmbt_irec uirec;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
xfs_filblks_t count_fsb;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error;
unsigned int resblks;
xfs_filblks_t ilen;
xfs_filblks_t rlen;
int nimaps;
xfs_extnum_t idx;
trace_xfs_reflink_end_cow(ip, offset, count);
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0)
return 0;
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
/* Start a rolling transaction to switch the mappings */
resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
@ -698,72 +621,61 @@ xfs_reflink_end_cow(
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* Go find the old extent in the CoW fork. */
while (offset_fsb < end_fsb) {
/* Read extent from the source file */
nimaps = 1;
count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
&nimaps, XFS_BMAPI_COWFORK);
if (error)
goto out_cancel;
ASSERT(nimaps == 1);
/* If there is a hole at end_fsb - 1 go to the previous extent */
if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
got.br_startoff > end_fsb) {
ASSERT(idx > 0);
xfs_iext_get_extent(ifp, --idx, &got);
}
ASSERT(irec.br_startblock != DELAYSTARTBLOCK);
trace_xfs_reflink_cow_remap(ip, &irec);
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/*
* We can have a hole in the CoW fork if part of a directio
* write is CoW but part of it isn't.
*/
rlen = ilen = irec.br_blockcount;
if (irec.br_startblock == HOLESTARTBLOCK)
/* Extent delete may have bumped idx forward */
if (!del.br_blockcount) {
idx--;
goto next_extent;
/* Unmap the old blocks in the data fork. */
while (rlen) {
xfs_defer_init(&dfops, &firstfsb);
error = __xfs_bunmapi(tp, ip, irec.br_startoff,
&rlen, 0, 1, &firstfsb, &dfops);
if (error)
goto out_defer;
/*
* Trim the extent to whatever got unmapped.
* Remember, bunmapi works backwards.
*/
uirec.br_startblock = irec.br_startblock + rlen;
uirec.br_startoff = irec.br_startoff + rlen;
uirec.br_blockcount = irec.br_blockcount - rlen;
irec.br_blockcount = rlen;
trace_xfs_reflink_cow_remap_piece(ip, &uirec);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp->t_mountp,
&dfops, uirec.br_startblock,
uirec.br_blockcount);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
ip, &uirec);
if (error)
goto out_defer;
/* Remove the mapping from the CoW fork. */
error = xfs_bunmapi_cow(ip, &uirec);
if (error)
goto out_defer;
error = xfs_defer_finish(&tp, &dfops, ip);
if (error)
goto out_defer;
}
ASSERT(!isnullstartblock(got.br_startblock));
/* Unmap the old blocks in the data fork. */
xfs_defer_init(&dfops, &firstfsb);
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/* Trim the extent to whatever got unmapped. */
if (rlen) {
xfs_trim_extent(&del, del.br_startoff + rlen,
del.br_blockcount - rlen);
}
trace_xfs_reflink_cow_remap(ip, &del);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
del.br_startblock, del.br_blockcount);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
if (error)
goto out_defer;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
error = xfs_defer_finish(&tp, &dfops, ip);
if (error)
goto out_defer;
next_extent:
/* Roll on... */
offset_fsb = irec.br_startoff + ilen;
if (!xfs_iext_get_extent(ifp, idx, &got))
break;
}
error = xfs_trans_commit(tp);
@ -774,7 +686,6 @@ next_extent:
out_defer:
xfs_defer_cancel(&dfops);
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
@ -1312,19 +1223,26 @@ out_error:
*/
int
xfs_reflink_remap_range(
struct xfs_inode *src,
xfs_off_t srcoff,
struct xfs_inode *dest,
xfs_off_t destoff,
xfs_off_t len,
unsigned int flags)
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
struct xfs_mount *mp = src->i_mount;
loff_t bs = inode_out->i_sb->s_blocksize;
bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
int error;
xfs_extlen_t cowextsize;
bool is_same;
loff_t isize;
ssize_t ret;
loff_t blen;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
@ -1332,17 +1250,8 @@ xfs_reflink_remap_range(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
return -EINVAL;
if (flags & ~XFS_REFLINK_ALL)
return -EINVAL;
trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
/* Lock both files against IO */
if (src->i_ino == dest->i_ino) {
if (same_inode) {
xfs_ilock(src, XFS_IOLOCK_EXCL);
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
} else {
@ -1350,39 +1259,132 @@ xfs_reflink_remap_range(
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
}
/* Don't touch certain kinds of inodes */
ret = -EPERM;
if (IS_IMMUTABLE(inode_out))
goto out_unlock;
ret = -ETXTBSY;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
goto out_unlock;
/* Don't reflink dirs, pipes, sockets... */
ret = -EISDIR;
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
goto out_unlock;
ret = -EINVAL;
if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
goto out_unlock;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
goto out_unlock;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
/* Are we going all the way to the end? */
isize = i_size_read(inode_in);
if (isize == 0) {
ret = 0;
goto out_unlock;
}
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (len == 0) {
if (is_dedupe) {
ret = 0;
goto out_unlock;
}
len = isize - pos_in;
}
/* Ensure offsets don't wrap and the input is inside i_size */
if (pos_in + len < pos_in || pos_out + len < pos_out ||
pos_in + len > isize)
goto out_unlock;
/* Don't allow dedupe past EOF in the dest file */
if (is_dedupe) {
loff_t disize;
disize = i_size_read(inode_out);
if (pos_out >= disize || pos_out + len > disize)
goto out_unlock;
}
/* If we're linking to EOF, continue to the block boundary. */
if (pos_in + len == isize)
blen = ALIGN(isize, bs) - pos_in;
else
blen = len;
/* Only reflink if we're aligned to block boundaries */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
!IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
goto out_unlock;
/* Don't allow overlapped reflink within the same file */
if (same_inode) {
if (pos_out + blen > pos_in && pos_out < pos_in + blen)
goto out_unlock;
}
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + len - 1);
if (ret)
goto out_unlock;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + len - 1);
if (ret)
goto out_unlock;
trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
/*
* Check that the extents are the same.
*/
if (flags & XFS_REFLINK_DEDUPE) {
is_same = false;
error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
destoff, len, &is_same);
if (error)
goto out_error;
if (is_dedupe) {
bool is_same = false;
ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out,
len, &is_same);
if (ret)
goto out_unlock;
if (!is_same) {
error = -EBADE;
goto out_error;
ret = -EBADE;
goto out_unlock;
}
}
error = xfs_reflink_set_inode_flag(src, dest);
if (error)
goto out_error;
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
/*
* Invalidate the page cache so that we can clear any CoW mappings
* in the destination file.
*/
truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff,
PAGE_ALIGN(destoff + len) - 1);
truncate_inode_pages_range(&inode_out->i_data, pos_out,
PAGE_ALIGN(pos_out + len) - 1);
dfsbno = XFS_B_TO_FSBT(mp, destoff);
sfsbno = XFS_B_TO_FSBT(mp, srcoff);
dfsbno = XFS_B_TO_FSBT(mp, pos_out);
sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
destoff + len);
if (error)
goto out_error;
ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
pos_out + len);
if (ret)
goto out_unlock;
/*
* Carry the cowextsize hint from src to dest if we're sharing the
@ -1390,26 +1392,24 @@ xfs_reflink_remap_range(
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
if (srcoff == 0 && len == i_size_read(VFS_I(src)) &&
if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
destoff == 0 && len >= i_size_read(VFS_I(dest)) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
error = xfs_reflink_update_dest(dest, destoff + len, cowextsize);
if (error)
goto out_error;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
out_error:
out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
xfs_iunlock(src, XFS_IOLOCK_EXCL);
if (src->i_ino != dest->i_ino) {
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
xfs_iunlock(dest, XFS_IOLOCK_EXCL);
}
if (error)
trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_);
return error;
if (ret)
trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
return ret;
}
/*
@ -1652,37 +1652,3 @@ out:
trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
return error;
}
/*
* Does this inode have any real CoW reservations?
*/
bool
xfs_reflink_has_real_cow_blocks(
struct xfs_inode *ip)
{
struct xfs_bmbt_irec irec;
struct xfs_ifork *ifp;
struct xfs_bmbt_rec_host *gotp;
xfs_extnum_t idx;
if (!xfs_is_reflink_inode(ip))
return false;
/* Go find the old extent in the CoW fork. */
ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
gotp = xfs_iext_bno_to_ext(ifp, 0, &idx);
while (gotp) {
xfs_bmbt_get_all(gotp, &irec);
if (!isnullstartblock(irec.br_startblock))
return true;
/* Roll on... */
idx++;
if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
break;
gotp = xfs_iext_get_ext(ifp, idx);
}
return false;
}

17
fs/xfs/xfs_reflink.h
View File

@ -26,13 +26,13 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
xfs_off_t offset, xfs_off_t count);
extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
struct xfs_bmbt_irec *imap, bool *shared);
extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
xfs_off_t offset, xfs_off_t count);
extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
struct xfs_bmbt_irec *imap, bool *need_alloc);
extern int xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
struct xfs_bmbt_irec *imap);
extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
@ -43,16 +43,11 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t count);
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */
#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE)
extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
unsigned int flags);
extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
struct xfs_trans **tpp);
extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t len);
extern bool xfs_reflink_has_real_cow_blocks(struct xfs_inode *ip);
#endif /* __XFS_REFLINK_H */

4
fs/xfs/xfs_sysfs.c
View File

@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
};
struct kobj_type xfs_error_cfg_ktype = {
static struct kobj_type xfs_error_cfg_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_error_attrs,
};
struct kobj_type xfs_error_ktype = {
static struct kobj_type xfs_error_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
};

4
fs/xfs/xfs_trace.h
View File

@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);

17
include/linux/iomap.h
View File

@ -19,11 +19,15 @@ struct vm_fault;
#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */
/*
* Flags for iomap mappings:
* Flags for all iomap mappings:
*/
#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */
#define IOMAP_F_SHARED 0x02 /* block shared with another file */
#define IOMAP_F_NEW 0x04 /* blocks have been newly allocated */
#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */
/*
* Flags that only need to be reported for IOMAP_REPORT requests:
*/
#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */
#define IOMAP_F_SHARED 0x20 /* block shared with another file */
/*
* Magic value for blkno:
@ -42,8 +46,9 @@ struct iomap {
/*
* Flags for iomap_begin / iomap_end. No flag implies a read.
*/
#define IOMAP_WRITE (1 << 0)
#define IOMAP_ZERO (1 << 1)
#define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */
#define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */
#define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */
#define IOMAP_FAULT (1 << 3) /* mapping for page fault */
struct iomap_ops {