summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iomap.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_iomap.c')
-rw-r--r--fs/xfs/xfs_iomap.c104
1 files changed, 64 insertions, 40 deletions
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 436e109bb01e..0d147428971e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -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));
@@ -563,8 +564,7 @@ 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;
@@ -595,35 +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;
@@ -631,8 +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*/
@@ -640,13 +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))
@@ -960,6 +950,19 @@ static inline bool imap_needs_alloc(struct inode *inode,
(IS_DAX(inode) && ISUNWRITTEN(imap));
}
+static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
+{
+ /*
+ * COW writes will allocate delalloc space, so we need to make sure
+ * to take the lock exclusively here.
+ */
+ if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
+ return true;
+ if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE))
+ return true;
+ return false;
+}
+
static int
xfs_file_iomap_begin(
struct inode *inode,
@@ -979,18 +982,14 @@ xfs_file_iomap_begin(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
- !xfs_get_extsz_hint(ip)) {
+ if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
+ !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
/* Reserve delalloc blocks for regular writeback. */
return xfs_file_iomap_begin_delay(inode, offset, length, flags,
iomap);
}
- /*
- * 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)) {
+ if (need_excl_ilock(ip, flags)) {
lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
} else {
@@ -1003,17 +1002,41 @@ xfs_file_iomap_begin(
offset_fsb = XFS_B_TO_FSBT(mp, offset);
end_fsb = XFS_B_TO_FSB(mp, offset + length);
+ if (xfs_is_reflink_inode(ip) &&
+ (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) {
+ shared = xfs_reflink_find_cow_mapping(ip, offset, &imap);
+ if (shared) {
+ xfs_iunlock(ip, lockmode);
+ goto alloc_done;
+ }
+ ASSERT(!isnullstartblock(imap.br_startblock));
+ }
+
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, 0);
if (error)
goto out_unlock;
- if (flags & IOMAP_REPORT) {
+ if ((flags & IOMAP_REPORT) ||
+ (xfs_is_reflink_inode(ip) &&
+ (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) {
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
&trimmed);
if (error)
goto out_unlock;
+
+ /*
+ * We're here because we're trying to do a directio write to a
+ * region that isn't aligned to a filesystem block. If the
+ * extent is shared, fall back to buffered mode to handle the
+ * RMW.
+ */
+ if (!(flags & IOMAP_REPORT) && shared) {
+ trace_xfs_reflink_bounce_dio_write(ip, &imap);
+ error = -EREMCHG;
+ goto out_unlock;
+ }
}
if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
@@ -1048,6 +1071,7 @@ xfs_file_iomap_begin(
if (error)
return error;
+alloc_done:
iomap->flags = IOMAP_F_NEW;
trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
} else {