}
/*
- * Buffered IO write completion for delayed allocate extents.
+ * IO write completion.
*/
STATIC void
-xfs_end_bio_delalloc(
- struct work_struct *work)
-{
- xfs_ioend_t *ioend =
- container_of(work, xfs_ioend_t, io_work);
-
- xfs_setfilesize(ioend);
- xfs_destroy_ioend(ioend);
-}
-
-/*
- * Buffered IO write completion for regular, written extents.
- */
-STATIC void
-xfs_end_bio_written(
- struct work_struct *work)
-{
- xfs_ioend_t *ioend =
- container_of(work, xfs_ioend_t, io_work);
-
- xfs_setfilesize(ioend);
- xfs_destroy_ioend(ioend);
-}
-
-/*
- * IO write completion for unwritten extents.
- *
- * Issue transactions to convert a buffer range from unwritten
- * to written extents.
- */
-STATIC void
-xfs_end_bio_unwritten(
+xfs_end_io(
struct work_struct *work)
{
xfs_ioend_t *ioend =
container_of(work, xfs_ioend_t, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
- xfs_off_t offset = ioend->io_offset;
- size_t size = ioend->io_size;
-
- if (likely(!ioend->io_error)) {
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- int error;
- error = xfs_iomap_write_unwritten(ip, offset, size);
- if (error)
- ioend->io_error = error;
- }
- xfs_setfilesize(ioend);
- }
- xfs_destroy_ioend(ioend);
-}
-/*
- * IO read completion for regular, written extents.
- */
-STATIC void
-xfs_end_bio_read(
- struct work_struct *work)
-{
- xfs_ioend_t *ioend =
- container_of(work, xfs_ioend_t, io_work);
+ /*
+ * For unwritten extents we need to issue transactions to convert a
+ * range to normal written extens after the data I/O has finished.
+ */
+ if (ioend->io_type == IOMAP_UNWRITTEN &&
+ likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
+ int error;
+
+ error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
+ ioend->io_size);
+ if (error)
+ ioend->io_error = error;
+ }
+ /*
+ * We might have to update the on-disk file size after extending
+ * writes.
+ */
+ if (ioend->io_type != IOMAP_READ)
+ xfs_setfilesize(ioend);
xfs_destroy_ioend(ioend);
}
int wait)
{
if (atomic_dec_and_test(&ioend->io_remaining)) {
- struct workqueue_struct *wq = xfsdatad_workqueue;
- if (ioend->io_work.func == xfs_end_bio_unwritten)
- wq = xfsconvertd_workqueue;
+ struct workqueue_struct *wq;
+ wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+ xfsconvertd_workqueue : xfsdatad_workqueue;
queue_work(wq, &ioend->io_work);
if (wait)
flush_workqueue(wq);
ioend->io_offset = 0;
ioend->io_size = 0;
- if (type == IOMAP_UNWRITTEN)
- INIT_WORK(&ioend->io_work, xfs_end_bio_unwritten);
- else if (type == IOMAP_DELAY)
- INIT_WORK(&ioend->io_work, xfs_end_bio_delalloc);
- else if (type == IOMAP_READ)
- INIT_WORK(&ioend->io_work, xfs_end_bio_read);
- else
- INIT_WORK(&ioend->io_work, xfs_end_bio_written);
-
+ INIT_WORK(&ioend->io_work, xfs_end_io);
return ioend;
}
return -xfs_iomap(XFS_I(inode), offset, count, flags, mapp, &nmaps);
}
-STATIC_INLINE int
+STATIC int
xfs_iomap_valid(
xfs_iomap_t *iomapp,
loff_t offset)
STATIC void
xfs_submit_ioend_bio(
- xfs_ioend_t *ioend,
- struct bio *bio)
+ struct writeback_control *wbc,
+ xfs_ioend_t *ioend,
+ struct bio *bio)
{
atomic_inc(&ioend->io_remaining);
bio->bi_private = ioend;
if (xfs_ioend_new_eof(ioend))
xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
- submit_bio(WRITE, bio);
+ submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC_PLUG : WRITE, bio);
ASSERT(!bio_flagged(bio, BIO_EOPNOTSUPP));
bio_put(bio);
}
*/
STATIC void
xfs_submit_ioend(
+ struct writeback_control *wbc,
xfs_ioend_t *ioend)
{
xfs_ioend_t *head = ioend;
retry:
bio = xfs_alloc_ioend_bio(bh);
} else if (bh->b_blocknr != lastblock + 1) {
- xfs_submit_ioend_bio(ioend, bio);
+ xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
if (bio_add_buffer(bio, bh) != bh->b_size) {
- xfs_submit_ioend_bio(ioend, bio);
+ xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
lastblock = bh->b_blocknr;
}
if (bio)
- xfs_submit_ioend_bio(ioend, bio);
+ xfs_submit_ioend_bio(wbc, ioend, bio);
xfs_finish_ioend(ioend, 0);
} while ((ioend = next) != NULL);
}
}
if (iohead)
- xfs_submit_ioend(iohead);
+ xfs_submit_ioend(wbc, iohead);
return page_dirty;
* didn't map an unwritten extent so switch it's completion
* handler.
*/
- INIT_WORK(&ioend->io_work, xfs_end_bio_written);
+ ioend->io_type = IOMAP_NEW;
xfs_finish_ioend(ioend, 0);
}
return mask;
}
-STATIC_INLINE void
+STATIC void
set_page_region(
struct page *page,
size_t offset,
SetPageUptodate(page);
}
-STATIC_INLINE int
+STATIC int
test_page_region(
struct page *page,
size_t offset,
* although backing storage may not be.
*/
xfs_buf_t *
-xfs_buf_get_flags(
+xfs_buf_get(
xfs_buftarg_t *target,/* target for buffer */
xfs_off_t ioff, /* starting offset of range */
size_t isize, /* length of range */
}
xfs_buf_t *
-xfs_buf_read_flags(
+xfs_buf_read(
xfs_buftarg_t *target,
xfs_off_t ioff,
size_t isize,
flags |= XBF_READ;
- bp = xfs_buf_get_flags(target, ioff, isize, flags);
+ bp = xfs_buf_get(target, ioff, isize, flags);
if (bp) {
if (!XFS_BUF_ISDONE(bp)) {
XB_TRACE(bp, "read", (unsigned long)flags);
return;
flags |= (XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
- xfs_buf_read_flags(target, ioff, isize, flags);
+ xfs_buf_read(target, ioff, isize, flags);
}
xfs_buf_t *
xfs_buf_delwri_queue(bp, 1);
}
-STATIC_INLINE void
+STATIC void
_xfs_buf_ioend(
xfs_buf_t *bp,
int schedule)
#define xfs_incore(buftarg,blkno,len,lockit) \
_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
-extern xfs_buf_t *xfs_buf_get_flags(xfs_buftarg_t *, xfs_off_t, size_t,
+extern xfs_buf_t *xfs_buf_get(xfs_buftarg_t *, xfs_off_t, size_t,
xfs_buf_flags_t);
-#define xfs_buf_get(target, blkno, len, flags) \
- xfs_buf_get_flags((target), (blkno), (len), XBF_LOCK | XBF_MAPPED)
-
-extern xfs_buf_t *xfs_buf_read_flags(xfs_buftarg_t *, xfs_off_t, size_t,
+extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
xfs_buf_flags_t);
-#define xfs_buf_read(target, blkno, len, flags) \
- xfs_buf_read_flags((target), (blkno), (len), XBF_LOCK | XBF_MAPPED)
extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *);
extern xfs_buf_t *xfs_buf_get_noaddr(size_t, xfs_buftarg_t *);
loff_t pos)
{
struct file *file = iocb->ki_filp;
- int ioflags = IO_ISAIO;
+ int ioflags = 0;
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
loff_t pos)
{
struct file *file = iocb->ki_filp;
- int ioflags = IO_ISAIO;
+ int ioflags = 0;
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
bf.l_len = len;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
- 0, XFS_ATTR_NOLOCK);
+ error = -xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
+ 0, XFS_ATTR_NOLOCK);
if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode))
new_size = offset + len;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
- error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
+ error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
iocb->ki_pos = *offset;
ret = generic_file_aio_read(iocb, iovp, segs, *offset);
- if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
- ret = wait_on_sync_kiocb(iocb);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
current->backing_dev_info = NULL;
- if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
- ret = wait_on_sync_kiocb(iocb);
-
isize = i_size_read(inode);
if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
*offset = isize;
*/
STATIC void
xfs_fs_destroy_inode(
- struct inode *inode)
+ struct inode *inode)
{
- xfs_inode_t *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(inode);
+
+ xfs_itrace_entry(ip);
XFS_STATS_INC(vn_reclaim);
- if (xfs_reclaim(ip))
- panic("%s: cannot reclaim 0x%p\n", __func__, inode);
+
+ /* bad inode, get out here ASAP */
+ if (is_bad_inode(inode))
+ goto out_reclaim;
+
+ xfs_ioend_wait(ip);
+
+ ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+
+ /*
+ * We should never get here with one of the reclaim flags already set.
+ */
+ ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+ ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
+
+ /*
+ * If we have nothing to flush with this inode then complete the
+ * teardown now, otherwise delay the flush operation.
+ */
+ if (!xfs_inode_clean(ip)) {
+ xfs_inode_set_reclaim_tag(ip);
+ return;
+ }
+
+out_reclaim:
+ xfs_ireclaim(ip);
}
/*
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
- mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
}
/*
XFS_STATS_INC(vn_remove);
XFS_STATS_DEC(vn_active);
+ /*
+ * The iolock is used by the file system to coordinate reads,
+ * writes, and block truncates. Up to this point the lock
+ * protected concurrent accesses by users of the inode. But
+ * from here forward we're doing some final processing of the
+ * inode because we're done with it, and although we reuse the
+ * iolock for protection it is really a distinct lock class
+ * (in the lockdep sense) from before. To keep lockdep happy
+ * (and basically indicate what we are doing), we explicitly
+ * re-init the iolock here.
+ */
+ ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+ mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
+
xfs_inactive(ip);
}
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
- struct xfs_inode *rip = mp->m_rootip;
- int unmount_event_flags = 0;
xfs_syncd_stop(mp);
xfs_sync_attr(mp, 0);
}
-#ifdef HAVE_DMAPI
- if (mp->m_flags & XFS_MOUNT_DMAPI) {
- unmount_event_flags =
- (mp->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ?
- 0 : DM_FLAGS_UNWANTED;
- /*
- * Ignore error from dmapi here, first unmount is not allowed
- * to fail anyway, and second we wouldn't want to fail a
- * unmount because of dmapi.
- */
- XFS_SEND_PREUNMOUNT(mp, rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
- NULL, NULL, 0, 0, unmount_event_flags);
- }
-#endif
+ XFS_SEND_PREUNMOUNT(mp);
/*
* Blow away any referenced inode in the filestreams cache.
XFS_bflush(mp->m_ddev_targp);
- if (mp->m_flags & XFS_MOUNT_DMAPI) {
- XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
- unmount_event_flags);
- }
+ XFS_SEND_UNMOUNT(mp);
xfs_unmountfs(mp);
xfs_freesb(mp);
kthread_stop(mp->m_sync_task);
}
-int
+STATIC int
xfs_reclaim_inode(
xfs_inode_t *ip,
- int locked,
int sync_mode)
{
xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
!__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
spin_unlock(&ip->i_flags_lock);
write_unlock(&pag->pag_ici_lock);
- if (locked) {
- xfs_ifunlock(ip);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
return -EAGAIN;
}
__xfs_iflags_set(ip, XFS_IRECLAIM);
* We get the flush lock regardless, though, just to make sure
* we don't free it while it is being flushed.
*/
- if (!locked) {
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_iflock(ip);
- }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_iflock(ip);
/*
* In the case of a forced shutdown we rely on xfs_iflush() to
}
read_unlock(&pag->pag_ici_lock);
- return xfs_reclaim_inode(ip, 0, flags);
+ return xfs_reclaim_inode(ip, flags);
}
int
void xfs_flush_inodes(struct xfs_inode *ip);
-int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
/*
* Flags for read/write calls - same values as IRIX
*/
-#define IO_ISAIO 0x00001 /* don't wait for completion */
#define IO_ISDIRECT 0x00004 /* bypass page cache */
#define IO_INVIS 0x00020 /* don't update inode timestamps */
# define STATIC static noinline
#endif
-#ifndef STATIC_INLINE
-# define STATIC_INLINE static inline
-#endif
-
#else /* DEBUG */
#define ASSERT(expr) \
# define STATIC noinline
#endif
-/*
- * We stop inlining of inline functions in debug mode.
- * Unfortunately, this means static inline in header files
- * get multiple definitions, so they need to remain static.
- * This then gives tonnes of warnings about unused but defined
- * functions, so we need to add the unused attribute to prevent
- * these spurious warnings.
- */
-#ifndef STATIC_INLINE
-# define STATIC_INLINE static __attribute__ ((unused)) noinline
-#endif
-
#endif /* DEBUG */
-
-
#endif /* __XFS_SUPPORT_DEBUG_H__ */
* Overall external interface routines.
*========================================================================*/
-int
-xfs_attr_fetch(xfs_inode_t *ip, struct xfs_name *name,
- char *value, int *valuelenp, int flags)
+STATIC int
+xfs_attr_get_int(
+ struct xfs_inode *ip,
+ struct xfs_name *name,
+ char *value,
+ int *valuelenp,
+ int flags)
{
xfs_da_args_t args;
int error;
return error;
xfs_ilock(ip, XFS_ILOCK_SHARED);
- error = xfs_attr_fetch(ip, &xname, value, valuelenp, flags);
+ error = xfs_attr_get_int(ip, &xname, value, valuelenp, flags);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return(error);
}
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
- bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, blkcnt,
- XFS_BUF_LOCK | XBF_DONT_BLOCK);
+ bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt,
+ XFS_BUF_LOCK | XBF_DONT_BLOCK);
ASSERT(bp);
ASSERT(!XFS_BUF_GETERROR(bp));
*/
int xfs_attr_calc_size(struct xfs_inode *, int, int, int *);
int xfs_attr_inactive(struct xfs_inode *dp);
-int xfs_attr_fetch(struct xfs_inode *, struct xfs_name *, char *, int *, int);
int xfs_attr_rmtval_get(struct xfs_da_args *args);
int xfs_attr_list_int(struct xfs_attr_list_context *);
* If namespace bits don't match return 0.
* If all match then return 1.
*/
-STATIC_INLINE int
+STATIC int
xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
{
return XFS_ATTR_NSP_ONDISK(ondisk_flags) == XFS_ATTR_NSP_ARGS_TO_ONDISK(arg_flags);
* This code must be in sync with the routines xfs_bmbt_get_startoff,
* xfs_bmbt_get_startblock, xfs_bmbt_get_blockcount and xfs_bmbt_get_state.
*/
-
-STATIC_INLINE void
+STATIC void
__xfs_bmbt_get_all(
__uint64_t l0,
__uint64_t l1,
* the cache that reference per-ag array elements that have since been
* reallocated.
*/
-STATIC_INLINE int
+static inline int
xfs_filestream_peek_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
return atomic_read(&mp->m_perag[agno].pagf_fstrms);
}
-STATIC_INLINE int
+static inline int
xfs_filestream_get_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
return atomic_inc_return(&mp->m_perag[agno].pagf_fstrms);
}
-STATIC_INLINE int
+static inline int
xfs_filestream_put_ag(
xfs_mount_t *mp,
xfs_agnumber_t agno)
/* filestreams for the inode? */
-STATIC_INLINE int
+static inline int
xfs_inode_is_filestream(
struct xfs_inode *ip)
{
* AG freelist header block
*/
bp = xfs_buf_get(mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0);
+ XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
+ XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED);
agf = XFS_BUF_TO_AGF(bp);
memset(agf, 0, mp->m_sb.sb_sectsize);
agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
* AG inode header block
*/
bp = xfs_buf_get(mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0);
+ XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
+ XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED);
agi = XFS_BUF_TO_AGI(bp);
memset(agi, 0, mp->m_sb.sb_sectsize);
agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
* BNO btree root block
*/
bp = xfs_buf_get(mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0);
+ XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
+ BTOBB(mp->m_sb.sb_blocksize),
+ XBF_LOCK | XBF_MAPPED);
block = XFS_BUF_TO_BLOCK(bp);
memset(block, 0, mp->m_sb.sb_blocksize);
block->bb_magic = cpu_to_be32(XFS_ABTB_MAGIC);
* CNT btree root block
*/
bp = xfs_buf_get(mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0);
+ XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
+ BTOBB(mp->m_sb.sb_blocksize),
+ XBF_LOCK | XBF_MAPPED);
block = XFS_BUF_TO_BLOCK(bp);
memset(block, 0, mp->m_sb.sb_blocksize);
block->bb_magic = cpu_to_be32(XFS_ABTC_MAGIC);
* INO btree root block
*/
bp = xfs_buf_get(mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0);
+ XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
+ BTOBB(mp->m_sb.sb_blocksize),
+ XBF_LOCK | XBF_MAPPED);
block = XFS_BUF_TO_BLOCK(bp);
memset(block, 0, mp->m_sb.sb_blocksize);
block->bb_magic = cpu_to_be32(XFS_IBT_MAGIC);
xfs_inode_t *ip;
int error;
- tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
+ tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP);
error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return 0;
}
-STATIC_INLINE xfs_agnumber_t
+STATIC xfs_agnumber_t
xfs_ialloc_next_ag(
xfs_mount_t *mp)
{
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
+ ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+
+ mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
/* initialise the xfs inode */
ip->i_ino = ino;
struct xfs_inode **ipp,
xfs_daddr_t bno,
int flags,
- int lock_flags) __releases(pag->pag_ici_lock)
+ int lock_flags)
{
struct xfs_inode *ip;
int error;
* set up a transaction to convert the range of extents
* from unwritten to real. Do allocations in a loop until
* we have covered the range passed in.
+ *
+ * Note that we open code the transaction allocation here
+ * to pass KM_NOFS--we can't risk to recursing back into
+ * the filesystem here as we might be asked to write out
+ * the same inode that we complete here and might deadlock
+ * on the iolock.
*/
- tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
+ xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
+ tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, resblks,
XFS_WRITE_LOG_RES(mp), 0,
xfs_daddr_t blkno;
int len;
ushort flags;
+ uint buf_flags;
buf_f = (xfs_buf_log_format_t *)item->ri_buf[0].i_addr;
}
mp = log->l_mp;
- if (flags & XFS_BLI_INODE_BUF) {
- bp = xfs_buf_read_flags(mp->m_ddev_targp, blkno, len,
- XFS_BUF_LOCK);
- } else {
- bp = xfs_buf_read(mp->m_ddev_targp, blkno, len, 0);
- }
+ buf_flags = XFS_BUF_LOCK;
+ if (!(flags & XFS_BLI_INODE_BUF))
+ buf_flags |= XFS_BUF_MAPPED;
+
+ bp = xfs_buf_read(mp->m_ddev_targp, blkno, len, buf_flags);
if (XFS_BUF_ISERROR(bp)) {
xfs_ioerror_alert("xlog_recover_do..(read#1)", log->l_mp,
bp, blkno);
goto error;
}
- bp = xfs_buf_read_flags(mp->m_ddev_targp, in_f->ilf_blkno,
- in_f->ilf_len, XFS_BUF_LOCK);
+ bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len,
+ XFS_BUF_LOCK);
if (XFS_BUF_ISERROR(bp)) {
xfs_ioerror_alert("xlog_recover_do..(read#2)", mp,
bp, in_f->ilf_blkno);
{
xlog_rec_header_t *rhead;
xfs_daddr_t blk_no;
- xfs_caddr_t bufaddr, offset;
+ xfs_caddr_t offset;
xfs_buf_t *hbp, *dbp;
int error = 0, h_size;
int bblks, split_bblks;
/*
* Check for header wrapping around physical end-of-log
*/
- offset = NULL;
+ offset = XFS_BUF_PTR(hbp);
split_hblks = 0;
wrapped_hblks = 0;
if (blk_no + hblks <= log->l_logBBsize) {
* - order is important.
*/
wrapped_hblks = hblks - split_hblks;
- bufaddr = XFS_BUF_PTR(hbp);
error = XFS_BUF_SET_PTR(hbp,
- bufaddr + BBTOB(split_hblks),
+ offset + BBTOB(split_hblks),
BBTOB(hblks - split_hblks));
if (error)
goto bread_err2;
if (error)
goto bread_err2;
- error = XFS_BUF_SET_PTR(hbp, bufaddr,
+ error = XFS_BUF_SET_PTR(hbp, offset,
BBTOB(hblks));
if (error)
goto bread_err2;
-
- if (!offset)
- offset = xlog_align(log, 0,
- wrapped_hblks, hbp);
}
rhead = (xlog_rec_header_t *)offset;
error = xlog_valid_rec_header(log, rhead,
} else {
/* This log record is split across the
* physical end of log */
- offset = NULL;
+ offset = XFS_BUF_PTR(dbp);
split_bblks = 0;
if (blk_no != log->l_logBBsize) {
/* some data is before the physical
* _first_, then the log start (LR header end)
* - order is important.
*/
- bufaddr = XFS_BUF_PTR(dbp);
error = XFS_BUF_SET_PTR(dbp,
- bufaddr + BBTOB(split_bblks),
+ offset + BBTOB(split_bblks),
BBTOB(bblks - split_bblks));
if (error)
goto bread_err2;
if (error)
goto bread_err2;
- error = XFS_BUF_SET_PTR(dbp, bufaddr, h_size);
+ error = XFS_BUF_SET_PTR(dbp, offset, h_size);
if (error)
goto bread_err2;
-
- if (!offset)
- offset = xlog_align(log, wrapped_hblks,
- bblks - split_bblks, dbp);
}
xlog_unpack_data(rhead, offset, log);
if ((error = xlog_recover_process_data(log, rhash,
sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;
- bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), extra_flags);
+ bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size),
+ extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
XFS_BUF_UNMANAGE(bp);
xfs_buf_relse(bp);
sector_size = mp->m_sb.sb_sectsize;
- bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), extra_flags);
+ bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR,
+ BTOBB(sector_size), extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB re-read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
return 0;
- tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
+ tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
XFS_DEFAULT_LOG_COUNT);
if (error) {
mutex_destroy(&mp->m_icsb_mutex);
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_lock_cntr(
xfs_icsb_cnts_t *icsbp)
{
}
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_unlock_cntr(
xfs_icsb_cnts_t *icsbp)
{
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_lock_all_counters(
xfs_mount_t *mp)
{
}
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_unlock_all_counters(
xfs_mount_t *mp)
{
xfs_send_unmount_t xfs_send_unmount;
} xfs_dmops_t;
+#define XFS_DMAPI_UNMOUNT_FLAGS(mp) \
+ (((mp)->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ? 0 : DM_FLAGS_UNWANTED)
+
#define XFS_SEND_DATA(mp, ev,ip,off,len,fl,lock) \
(*(mp)->m_dm_ops->xfs_send_data)(ev,ip,off,len,fl,lock)
#define XFS_SEND_MMAP(mp, vma,fl) \
(*(mp)->m_dm_ops->xfs_send_destroy)(ip,right)
#define XFS_SEND_NAMESP(mp, ev,b1,r1,b2,r2,n1,n2,mode,rval,fl) \
(*(mp)->m_dm_ops->xfs_send_namesp)(ev,NULL,b1,r1,b2,r2,n1,n2,mode,rval,fl)
-#define XFS_SEND_PREUNMOUNT(mp,b1,r1,b2,r2,n1,n2,mode,rval,fl) \
- (*(mp)->m_dm_ops->xfs_send_namesp)(DM_EVENT_PREUNMOUNT,mp,b1,r1,b2,r2,n1,n2,mode,rval,fl)
#define XFS_SEND_MOUNT(mp,right,path,name) \
(*(mp)->m_dm_ops->xfs_send_mount)(mp,right,path,name)
-#define XFS_SEND_UNMOUNT(mp, ip,right,mode,rval,fl) \
- (*(mp)->m_dm_ops->xfs_send_unmount)(mp,ip,right,mode,rval,fl)
+#define XFS_SEND_PREUNMOUNT(mp) \
+do { \
+ if (mp->m_flags & XFS_MOUNT_DMAPI) { \
+ (*(mp)->m_dm_ops->xfs_send_namesp)(DM_EVENT_PREUNMOUNT, mp, \
+ (mp)->m_rootip, DM_RIGHT_NULL, \
+ (mp)->m_rootip, DM_RIGHT_NULL, \
+ NULL, NULL, 0, 0, XFS_DMAPI_UNMOUNT_FLAGS(mp)); \
+ } \
+} while (0)
+#define XFS_SEND_UNMOUNT(mp) \
+do { \
+ if (mp->m_flags & XFS_MOUNT_DMAPI) { \
+ (*(mp)->m_dm_ops->xfs_send_unmount)(mp, (mp)->m_rootip, \
+ DM_RIGHT_NULL, 0, 0, XFS_DMAPI_UNMOUNT_FLAGS(mp)); \
+ } \
+} while (0)
#ifdef HAVE_PERCPU_SB
* Per-cpu superblock locking functions
*/
#ifdef HAVE_PERCPU_SB
-STATIC_INLINE void
+static inline void
xfs_icsb_lock(xfs_mount_t *mp)
{
mutex_lock(&mp->m_icsb_mutex);
}
-STATIC_INLINE void
+static inline void
xfs_icsb_unlock(xfs_mount_t *mp)
{
mutex_unlock(&mp->m_icsb_mutex);
xfs_buf_t *bp;
int error;
- if (flags)
- bp = xfs_buf_read_flags(target, blkno, len, flags);
- else
- bp = xfs_buf_read(target, blkno, len, flags);
+ if (!flags)
+ flags = XBF_LOCK | XBF_MAPPED;
+
+ bp = xfs_buf_read(target, blkno, len, flags);
if (!bp)
return XFS_ERROR(EIO);
error = XFS_BUF_GETERROR(bp);
}
return (error);
}
+
+/*
+ * helper function to extract extent size hint from inode
+ */
+xfs_extlen_t
+xfs_get_extsz_hint(
+ struct xfs_inode *ip)
+{
+ xfs_extlen_t extsz;
+
+ if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
+ extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
+ ? ip->i_d.di_extsize
+ : ip->i_mount->m_sb.sb_rextsize;
+ ASSERT(extsz);
+ } else {
+ extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
+ ? ip->i_d.di_extsize : 0;
+ }
+
+ return extsz;
+}
}
/*
- * Flags for xfs_free_eofblocks
- */
-#define XFS_FREE_EOF_LOCK (1<<0)
-#define XFS_FREE_EOF_NOLOCK (1<<1)
-
-
-/*
- * helper function to extract extent size hint from inode
- */
-STATIC_INLINE xfs_extlen_t
-xfs_get_extsz_hint(
- xfs_inode_t *ip)
-{
- xfs_extlen_t extsz;
-
- if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
- extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
- ? ip->i_d.di_extsize
- : ip->i_mount->m_sb.sb_rextsize;
- ASSERT(extsz);
- } else {
- extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
- ? ip->i_d.di_extsize : 0;
- }
- return extsz;
-}
-
-/*
* Prototypes for functions in xfs_rw.c.
*/
extern int xfs_write_clear_setuid(struct xfs_inode *ip);
struct xfs_buf **bpp);
extern void xfs_ioerror_alert(char *func, struct xfs_mount *mp,
xfs_buf_t *bp, xfs_daddr_t blkno);
+extern xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
#endif /* __XFS_RW_H__ */
uint type)
{
xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
- return _xfs_trans_alloc(mp, type);
+ return _xfs_trans_alloc(mp, type, KM_SLEEP);
}
xfs_trans_t *
_xfs_trans_alloc(
xfs_mount_t *mp,
- uint type)
+ uint type,
+ uint memflags)
{
xfs_trans_t *tp;
atomic_inc(&mp->m_active_trans);
- tp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP);
+ tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
tp->t_magic = XFS_TRANS_MAGIC;
tp->t_type = type;
tp->t_mountp = mp;
* XFS transaction mechanism exported interfaces.
*/
xfs_trans_t *xfs_trans_alloc(struct xfs_mount *, uint);
-xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint);
+xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint, uint);
xfs_trans_t *xfs_trans_dup(xfs_trans_t *);
int xfs_trans_reserve(xfs_trans_t *, uint, uint, uint,
uint, uint);
/*
* Default to a normal get_buf() call if the tp is NULL.
*/
- if (tp == NULL) {
- bp = xfs_buf_get_flags(target_dev, blkno, len,
- flags | BUF_BUSY);
- return(bp);
- }
+ if (tp == NULL)
+ return xfs_buf_get(target_dev, blkno, len, flags | BUF_BUSY);
/*
* If we find the buffer in the cache with this transaction
* easily deadlock with our current transaction as well as cause
* us to run out of stack space.
*/
- bp = xfs_buf_get_flags(target_dev, blkno, len, flags | BUF_BUSY);
+ bp = xfs_buf_get(target_dev, blkno, len, flags | BUF_BUSY);
if (bp == NULL) {
return NULL;
}
* Default to a normal get_buf() call if the tp is NULL.
*/
if (tp == NULL) {
- bp = xfs_buf_read_flags(target, blkno, len, flags | BUF_BUSY);
+ bp = xfs_buf_read(target, blkno, len, flags | BUF_BUSY);
if (!bp)
return (flags & XFS_BUF_TRYLOCK) ?
EAGAIN : XFS_ERROR(ENOMEM);
* easily deadlock with our current transaction as well as cause
* us to run out of stack space.
*/
- bp = xfs_buf_read_flags(target, blkno, len, flags | BUF_BUSY);
+ bp = xfs_buf_read(target, blkno, len, flags | BUF_BUSY);
if (bp == NULL) {
*bpp = NULL;
return 0;
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
- bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt),
- XBF_LOCK | XBF_MAPPED |
- XBF_DONT_BLOCK);
+ bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt),
+ XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK);
error = XFS_BUF_GETERROR(bp);
if (error) {
xfs_ioerror_alert("xfs_readlink",
}
/*
+ * Flags for xfs_free_eofblocks
+ */
+#define XFS_FREE_EOF_TRYLOCK (1<<0)
+
+/*
* This is called by xfs_inactive to free any blocks beyond eof
* when the link count isn't zero and by xfs_dm_punch_hole() when
* punching a hole to EOF.
xfs_filblks_t map_len;
int nimaps;
xfs_bmbt_irec_t imap;
- int use_iolock = (flags & XFS_FREE_EOF_LOCK);
/*
* Figure out if there are any blocks beyond the end
* cache and we can't
* do that within a transaction.
*/
- if (use_iolock)
+ if (flags & XFS_FREE_EOF_TRYLOCK) {
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+ xfs_trans_cancel(tp, 0);
+ return 0;
+ }
+ } else {
xfs_ilock(ip, XFS_IOLOCK_EXCL);
+ }
error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE,
ip->i_size);
if (error) {
xfs_trans_cancel(tp, 0);
- if (use_iolock)
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES);
}
- xfs_iunlock(ip, (use_iolock ? (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)
- : XFS_ILOCK_EXCL));
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL);
}
return error;
}
(ip->i_df.if_flags & XFS_IFEXTENTS)) &&
(!(ip->i_d.di_flags &
(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) {
- error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK);
+
+ /*
+ * If we can't get the iolock just skip truncating
+ * the blocks past EOF because we could deadlock
+ * with the mmap_sem otherwise. We'll get another
+ * chance to drop them once the last reference to
+ * the inode is dropped, so we'll never leak blocks
+ * permanently.
+ */
+ error = xfs_free_eofblocks(mp, ip,
+ XFS_FREE_EOF_TRYLOCK);
if (error)
return error;
}
(!(ip->i_d.di_flags &
(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) ||
(ip->i_delayed_blks != 0)))) {
- error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK);
+ error = xfs_free_eofblocks(mp, ip, 0);
if (error)
return VN_INACTIVE_CACHE;
}
return error;
}
-int
-xfs_reclaim(
- xfs_inode_t *ip)
-{
-
- xfs_itrace_entry(ip);
-
- ASSERT(!VN_MAPPED(VFS_I(ip)));
-
- /* bad inode, get out here ASAP */
- if (is_bad_inode(VFS_I(ip))) {
- xfs_ireclaim(ip);
- return 0;
- }
-
- xfs_ioend_wait(ip);
-
- ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
-
- /*
- * If we have nothing to flush with this inode then complete the
- * teardown now, otherwise break the link between the xfs inode and the
- * linux inode and clean up the xfs inode later. This avoids flushing
- * the inode to disk during the delete operation itself.
- *
- * When breaking the link, we need to set the XFS_IRECLAIMABLE flag
- * first to ensure that xfs_iunpin() will never see an xfs inode
- * that has a linux inode being reclaimed. Synchronisation is provided
- * by the i_flags_lock.
- */
- if (!ip->i_update_core && (ip->i_itemp == NULL)) {
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_iflock(ip);
- xfs_iflags_set(ip, XFS_IRECLAIMABLE);
- return xfs_reclaim_inode(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
- }
- xfs_inode_set_reclaim_tag(ip);
- return 0;
-}
-
/*
* xfs_alloc_file_space()
* This routine allocates disk space for the given file.
const char *target_path, mode_t mode, struct xfs_inode **ipp,
cred_t *credp);
int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
-int xfs_reclaim(struct xfs_inode *ip);
int xfs_change_file_space(struct xfs_inode *ip, int cmd,
xfs_flock64_t *bf, xfs_off_t offset, int attr_flags);
int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,