aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/linux-2.6')
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c161
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c14
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.h9
-rw-r--r--fs/xfs/linux-2.6/xfs_file.c13
-rw-r--r--fs/xfs/linux-2.6/xfs_iops.c47
-rw-r--r--fs/xfs/linux-2.6/xfs_lrw.c9
-rw-r--r--fs/xfs/linux-2.6/xfs_quotaops.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c130
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c51
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.h1
-rw-r--r--fs/xfs/linux-2.6/xfs_sysctl.c62
-rw-r--r--fs/xfs/linux-2.6/xfs_vnode.h1
12 files changed, 231 insertions, 269 deletions
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 381854461b28..87813e405cef 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -186,19 +186,37 @@ xfs_destroy_ioend(
}
/*
+ * If the end of the current ioend is beyond the current EOF,
+ * return the new EOF value, otherwise zero.
+ */
+STATIC xfs_fsize_t
+xfs_ioend_new_eof(
+ xfs_ioend_t *ioend)
+{
+ xfs_inode_t *ip = XFS_I(ioend->io_inode);
+ xfs_fsize_t isize;
+ xfs_fsize_t bsize;
+
+ bsize = ioend->io_offset + ioend->io_size;
+ isize = MAX(ip->i_size, ip->i_new_size);
+ isize = MIN(isize, bsize);
+ return isize > ip->i_d.di_size ? isize : 0;
+}
+
+/*
* Update on-disk file size now that data has been written to disk.
* The current in-memory file size is i_size. If a write is beyond
* eof i_new_size will be the intended file size until i_size is
* updated. If this write does not extend all the way to the valid
* file size then restrict this update to the end of the write.
*/
+
STATIC void
xfs_setfilesize(
xfs_ioend_t *ioend)
{
xfs_inode_t *ip = XFS_I(ioend->io_inode);
xfs_fsize_t isize;
- xfs_fsize_t bsize;
ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
ASSERT(ioend->io_type != IOMAP_READ);
@@ -206,16 +224,10 @@ xfs_setfilesize(
if (unlikely(ioend->io_error))
return;
- bsize = ioend->io_offset + ioend->io_size;
-
xfs_ilock(ip, XFS_ILOCK_EXCL);
-
- isize = MAX(ip->i_size, ip->i_new_size);
- isize = MIN(isize, bsize);
-
- if (ip->i_d.di_size < isize) {
+ isize = xfs_ioend_new_eof(ioend);
+ if (isize) {
ip->i_d.di_size = isize;
- ip->i_update_core = 1;
xfs_mark_inode_dirty_sync(ip);
}
@@ -223,71 +235,36 @@ xfs_setfilesize(
}
/*
- * 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);
}
@@ -302,10 +279,10 @@ xfs_finish_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);
@@ -343,15 +320,7 @@ xfs_alloc_ioend(
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;
}
@@ -368,7 +337,7 @@ xfs_map_blocks(
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)
@@ -400,15 +369,23 @@ xfs_end_bio(
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;
bio->bi_end_io = xfs_end_bio;
- submit_bio(WRITE, bio);
+ /*
+ * If the I/O is beyond EOF we mark the inode dirty immediately
+ * but don't update the inode size until I/O completion.
+ */
+ if (xfs_ioend_new_eof(ioend))
+ xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
+
+ submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC_PLUG : WRITE, bio);
ASSERT(!bio_flagged(bio, BIO_EOPNOTSUPP));
bio_put(bio);
}
@@ -487,6 +464,7 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
*/
STATIC void
xfs_submit_ioend(
+ struct writeback_control *wbc,
xfs_ioend_t *ioend)
{
xfs_ioend_t *head = ioend;
@@ -515,19 +493,19 @@ xfs_submit_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);
}
@@ -886,16 +864,9 @@ xfs_convert_page(
if (startio) {
if (count) {
- struct backing_dev_info *bdi;
-
- bdi = inode->i_mapping->backing_dev_info;
wbc->nr_to_write--;
- if (bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
+ if (wbc->nr_to_write <= 0)
done = 1;
- } else if (wbc->nr_to_write <= 0) {
- done = 1;
- }
}
xfs_start_page_writeback(page, !page_dirty, count);
}
@@ -1180,7 +1151,7 @@ xfs_page_state_convert(
}
if (iohead)
- xfs_submit_ioend(iohead);
+ xfs_submit_ioend(wbc, iohead);
return page_dirty;
@@ -1517,7 +1488,7 @@ xfs_end_io_direct(
* 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);
}
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 965df1227d64..4ddc973aea7a 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -149,7 +149,7 @@ page_region_mask(
return mask;
}
-STATIC_INLINE void
+STATIC void
set_page_region(
struct page *page,
size_t offset,
@@ -161,7 +161,7 @@ set_page_region(
SetPageUptodate(page);
}
-STATIC_INLINE int
+STATIC int
test_page_region(
struct page *page,
size_t offset,
@@ -582,7 +582,7 @@ found:
* 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 */
@@ -661,7 +661,7 @@ _xfs_buf_read(
}
xfs_buf_t *
-xfs_buf_read_flags(
+xfs_buf_read(
xfs_buftarg_t *target,
xfs_off_t ioff,
size_t isize,
@@ -671,7 +671,7 @@ xfs_buf_read_flags(
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);
@@ -718,7 +718,7 @@ xfs_buf_readahead(
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 *
@@ -1113,7 +1113,7 @@ xfs_bdwrite(
xfs_buf_delwri_queue(bp, 1);
}
-STATIC_INLINE void
+STATIC void
_xfs_buf_ioend(
xfs_buf_t *bp,
int schedule)
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 9b4d666ad31f..5f07dd91c5fa 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -186,15 +186,10 @@ extern xfs_buf_t *_xfs_buf_find(xfs_buftarg_t *, xfs_off_t, size_t,
#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 *);
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 629370974e57..e4caeb28ce2e 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -52,7 +52,7 @@ xfs_file_aio_read(
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))
@@ -71,7 +71,7 @@ xfs_file_aio_write(
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))
@@ -176,14 +176,7 @@ xfs_file_fsync(
struct dentry *dentry,
int datasync)
{
- struct inode *inode = dentry->d_inode;
- struct xfs_inode *ip = XFS_I(inode);
- int error;
-
- /* capture size updates in I/O completion before writing the inode. */
- error = filemap_fdatawait(inode->i_mapping);
- if (error)
- return error;
+ struct xfs_inode *ip = XFS_I(dentry->d_inode);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
return -xfs_fsync(ip);
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index da0159d99f82..1f3b4b8f7dd4 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -57,19 +57,22 @@
#include <linux/fiemap.h>
/*
- * Bring the atime in the XFS inode uptodate.
- * Used before logging the inode to disk or when the Linux inode goes away.
+ * Bring the timestamps in the XFS inode uptodate.
+ *
+ * Used before writing the inode to disk.
*/
void
-xfs_synchronize_atime(
+xfs_synchronize_times(
xfs_inode_t *ip)
{
struct inode *inode = VFS_I(ip);
- if (!(inode->i_state & I_CLEAR)) {
- ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
- ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
- }
+ ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
+ ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
+ ip->i_d.di_ctime.t_sec = (__int32_t)inode->i_ctime.tv_sec;
+ ip->i_d.di_ctime.t_nsec = (__int32_t)inode->i_ctime.tv_nsec;
+ ip->i_d.di_mtime.t_sec = (__int32_t)inode->i_mtime.tv_sec;
+ ip->i_d.di_mtime.t_nsec = (__int32_t)inode->i_mtime.tv_nsec;
}
/*
@@ -106,32 +109,20 @@ xfs_ichgtime(
if ((flags & XFS_ICHGTIME_MOD) &&
!timespec_equal(&inode->i_mtime, &tv)) {
inode->i_mtime = tv;
- ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
- ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
sync_it = 1;
}
if ((flags & XFS_ICHGTIME_CHG) &&
!timespec_equal(&inode->i_ctime, &tv)) {
inode->i_ctime = tv;
- ip->i_d.di_ctime.t_sec = (__int32_t)tv.tv_sec;
- ip->i_d.di_ctime.t_nsec = (__int32_t)tv.tv_nsec;
sync_it = 1;
}
/*
- * We update the i_update_core field _after_ changing
- * the timestamps in order to coordinate properly with
- * xfs_iflush() so that we don't lose timestamp updates.
- * This keeps us from having to hold the inode lock
- * while doing this. We use the SYNCHRONIZE macro to
- * ensure that the compiler does not reorder the update
- * of i_update_core above the timestamp updates above.
+ * Update complete - now make sure everyone knows that the inode
+ * is dirty.
*/
- if (sync_it) {
- SYNCHRONIZE();
- ip->i_update_core = 1;
+ if (sync_it)
xfs_mark_inode_dirty_sync(ip);
- }
}
/*
@@ -506,10 +497,8 @@ xfs_vn_getattr(
stat->gid = ip->i_d.di_gid;
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
- stat->mtime.tv_sec = ip->i_d.di_mtime.t_sec;
- stat->mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
- stat->ctime.tv_sec = ip->i_d.di_ctime.t_sec;
- stat->ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
+ stat->mtime = inode->i_mtime;
+ stat->ctime = inode->i_ctime;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
@@ -584,8 +573,8 @@ xfs_vn_fallocate(
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;
@@ -596,7 +585,7 @@ xfs_vn_fallocate(
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);
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 49e4a6aea73c..1bf47f219c97 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -255,8 +255,6 @@ xfs_read(
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);
@@ -667,7 +665,7 @@ start:
xip->i_new_size = new_size;
if (likely(!(ioflags & IO_INVIS)))
- xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ file_update_time(file);
/*
* If the offset is beyond the size of the file, we have a couple
@@ -774,9 +772,6 @@ write_retry:
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;
@@ -811,7 +806,7 @@ write_retry:
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
- if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
+ if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
loff_t end = pos + ret - 1;
int error2;
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index 9e41f91aa269..3d4a0c84d634 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -80,7 +80,7 @@ xfs_fs_set_xstate(
if (sb->s_flags & MS_RDONLY)
return -EROFS;
- if (!XFS_IS_QUOTA_RUNNING(mp))
+ if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp))
return -ENOSYS;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index bdd41c8c342f..1bfb0e980193 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -930,13 +930,39 @@ xfs_fs_alloc_inode(
*/
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);
}
/*
@@ -973,7 +999,28 @@ xfs_fs_inode_init_once(
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);
+}
+
+/*
+ * Dirty the XFS inode when mark_inode_dirty_sync() is called so that
+ * we catch unlogged VFS level updates to the inode. Care must be taken
+ * here - the transaction code calls mark_inode_dirty_sync() to mark the
+ * VFS inode dirty in a transaction and clears the i_update_core field;
+ * it must clear the field after calling mark_inode_dirty_sync() to
+ * correctly indicate that the dirty state has been propagated into the
+ * inode log item.
+ *
+ * We need the barrier() to maintain correct ordering between unlogged
+ * updates and the transaction commit code that clears the i_update_core
+ * field. This requires all updates to be completed before marking the
+ * inode dirty.
+ */
+STATIC void
+xfs_fs_dirty_inode(
+ struct inode *inode)
+{
+ barrier();
+ XFS_I(inode)->i_update_core = 1;
}
/*
@@ -1053,6 +1100,20 @@ xfs_fs_clear_inode(
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);
}
@@ -1070,8 +1131,6 @@ xfs_fs_put_super(
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);
@@ -1087,20 +1146,7 @@ xfs_fs_put_super(
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.
@@ -1111,10 +1157,7 @@ xfs_fs_put_super(
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);
@@ -1126,7 +1169,7 @@ xfs_fs_put_super(
}
STATIC int
-xfs_fs_sync_super(
+xfs_fs_sync_fs(
struct super_block *sb,
int wait)
{
@@ -1134,23 +1177,23 @@ xfs_fs_sync_super(
int error;
/*
- * Treat a sync operation like a freeze. This is to work
- * around a race in sync_inodes() which works in two phases
- * - an asynchronous flush, which can write out an inode
- * without waiting for file size updates to complete, and a
- * synchronous flush, which wont do anything because the
- * async flush removed the inode's dirty flag. Also
- * sync_inodes() will not see any files that just have
- * outstanding transactions to be flushed because we don't
- * dirty the Linux inode until after the transaction I/O
- * completes.
+ * Not much we can do for the first async pass. Writing out the
+ * superblock would be counter-productive as we are going to redirty
+ * when writing out other data and metadata (and writing out a single
+ * block is quite fast anyway).
+ *
+ * Try to asynchronously kick off quota syncing at least.
*/
- if (wait || unlikely(sb->s_frozen == SB_FREEZE_WRITE))
- error = xfs_quiesce_data(mp);
- else
- error = xfs_sync_fsdata(mp, 0);
+ if (!wait) {
+ xfs_qm_sync(mp, SYNC_TRYLOCK);
+ return 0;
+ }
+
+ error = xfs_quiesce_data(mp);
+ if (error)
+ return -error;
- if (unlikely(laptop_mode)) {
+ if (laptop_mode) {
int prev_sync_seq = mp->m_sync_seq;
/*
@@ -1169,7 +1212,7 @@ xfs_fs_sync_super(
mp->m_sync_seq != prev_sync_seq);
}
- return -error;
+ return 0;
}
STATIC int
@@ -1539,10 +1582,11 @@ xfs_fs_get_sb(
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
+ .dirty_inode = xfs_fs_dirty_inode,
.write_inode = xfs_fs_write_inode,
.clear_inode = xfs_fs_clear_inode,
.put_super = xfs_fs_put_super,
- .sync_fs = xfs_fs_sync_super,
+ .sync_fs = xfs_fs_sync_fs,
.freeze_fs = xfs_fs_freeze,
.statfs = xfs_fs_statfs,
.remount_fs = xfs_fs_remount,
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 320be6aea492..d895a3a960f5 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -309,11 +309,15 @@ xfs_sync_attr(
STATIC int
xfs_commit_dummy_trans(
struct xfs_mount *mp,
- uint log_flags)
+ uint flags)
{
struct xfs_inode *ip = mp->m_rootip;
struct xfs_trans *tp;
int error;
+ int log_flags = XFS_LOG_FORCE;
+
+ if (flags & SYNC_WAIT)
+ log_flags |= XFS_LOG_SYNC;
/*
* Put a dummy transaction in the log to tell recovery
@@ -331,13 +335,12 @@ xfs_commit_dummy_trans(
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- /* XXX(hch): ignoring the error here.. */
error = xfs_trans_commit(tp, 0);
-
xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ /* the log force ensures this transaction is pushed to disk */
xfs_log_force(mp, 0, log_flags);
- return 0;
+ return error;
}
int
@@ -385,7 +388,20 @@ xfs_sync_fsdata(
else
XFS_BUF_ASYNC(bp);
- return xfs_bwrite(mp, bp);
+ error = xfs_bwrite(mp, bp);
+ if (error)
+ return error;
+
+ /*
+ * If this is a data integrity sync make sure all pending buffers
+ * are flushed out for the log coverage check below.
+ */
+ if (flags & SYNC_WAIT)
+ xfs_flush_buftarg(mp->m_ddev_targp, 1);
+
+ if (xfs_log_need_covered(mp))
+ error = xfs_commit_dummy_trans(mp, flags);
+ return error;
out_brelse:
xfs_buf_relse(bp);
@@ -419,14 +435,16 @@ xfs_quiesce_data(
/* push non-blocking */
xfs_sync_data(mp, 0);
xfs_qm_sync(mp, SYNC_TRYLOCK);
- xfs_filestream_flush(mp);
- /* push and block */
+ /* push and block till complete */
xfs_sync_data(mp, SYNC_WAIT);
xfs_qm_sync(mp, SYNC_WAIT);
+ /* drop inode references pinned by filestreams */
+ xfs_filestream_flush(mp);
+
/* write superblock and hoover up shutdown errors */
- error = xfs_sync_fsdata(mp, 0);
+ error = xfs_sync_fsdata(mp, SYNC_WAIT);
/* flush data-only devices */
if (mp->m_rtdev_targp)
@@ -570,8 +588,6 @@ xfs_sync_worker(
/* dgc: errors ignored here */
error = xfs_qm_sync(mp, SYNC_TRYLOCK);
error = xfs_sync_fsdata(mp, SYNC_TRYLOCK);
- if (xfs_log_need_covered(mp))
- error = xfs_commit_dummy_trans(mp, XFS_LOG_FORCE);
}
mp->m_sync_seq++;
wake_up(&mp->m_wait_single_sync_task);
@@ -647,10 +663,9 @@ xfs_syncd_stop(
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);
@@ -666,10 +681,6 @@ xfs_reclaim_inode(
!__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);
@@ -688,10 +699,8 @@ xfs_reclaim_inode(
* 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
@@ -762,7 +771,7 @@ xfs_reclaim_inode_now(
}
read_unlock(&pag->pag_ici_lock);
- return xfs_reclaim_inode(ip, 0, flags);
+ return xfs_reclaim_inode(ip, flags);
}
int
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 27920eb7a820..a500b4d91835 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -44,7 +44,6 @@ void xfs_quiesce_attr(struct xfs_mount *mp);
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);
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index c5bc67c4e3bb..7bb5092d6ae4 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -55,170 +55,140 @@ xfs_stats_clear_proc_handler(
static ctl_table xfs_table[] = {
{
- .ctl_name = XFS_SGID_INHERIT,
.procname = "irix_sgid_inherit",
.data = &xfs_params.sgid_inherit.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.sgid_inherit.min,
.extra2 = &xfs_params.sgid_inherit.max
},
{
- .ctl_name = XFS_SYMLINK_MODE,
.procname = "irix_symlink_mode",
.data = &xfs_params.symlink_mode.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.symlink_mode.min,
.extra2 = &xfs_params.symlink_mode.max
},
{
- .ctl_name = XFS_PANIC_MASK,
.procname = "panic_mask",
.data = &xfs_params.panic_mask.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.panic_mask.min,
.extra2 = &xfs_params.panic_mask.max
},
{
- .ctl_name = XFS_ERRLEVEL,
.procname = "error_level",
.data = &xfs_params.error_level.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.error_level.min,
.extra2 = &xfs_params.error_level.max
},
{
- .ctl_name = XFS_SYNCD_TIMER,
.procname = "xfssyncd_centisecs",
.data = &xfs_params.syncd_timer.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.syncd_timer.min,
.extra2 = &xfs_params.syncd_timer.max
},
{
- .ctl_name = XFS_INHERIT_SYNC,
.procname = "inherit_sync",
.data = &xfs_params.inherit_sync.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.inherit_sync.min,
.extra2 = &xfs_params.inherit_sync.max
},
{
- .ctl_name = XFS_INHERIT_NODUMP,
.procname = "inherit_nodump",
.data = &xfs_params.inherit_nodump.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.inherit_nodump.min,
.extra2 = &xfs_params.inherit_nodump.max
},
{
- .ctl_name = XFS_INHERIT_NOATIME,
.procname = "inherit_noatime",
.data = &xfs_params.inherit_noatim.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.inherit_noatim.min,
.extra2 = &xfs_params.inherit_noatim.max
},
{
- .ctl_name = XFS_BUF_TIMER,
.procname = "xfsbufd_centisecs",
.data = &xfs_params.xfs_buf_timer.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.xfs_buf_timer.min,
.extra2 = &xfs_params.xfs_buf_timer.max
},
{
- .ctl_name = XFS_BUF_AGE,
.procname = "age_buffer_centisecs",
.data = &xfs_params.xfs_buf_age.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.xfs_buf_age.min,
.extra2 = &xfs_params.xfs_buf_age.max
},
{
- .ctl_name = XFS_INHERIT_NOSYM,
.procname = "inherit_nosymlinks",
.data = &xfs_params.inherit_nosym.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.inherit_nosym.min,
.extra2 = &xfs_params.inherit_nosym.max
},
{
- .ctl_name = XFS_ROTORSTEP,
.procname = "rotorstep",
.data = &xfs_params.rotorstep.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.rotorstep.min,
.extra2 = &xfs_params.rotorstep.max
},
{
- .ctl_name = XFS_INHERIT_NODFRG,
.procname = "inherit_nodefrag",
.data = &xfs_params.inherit_nodfrg.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.inherit_nodfrg.min,
.extra2 = &xfs_params.inherit_nodfrg.max
},
{
- .ctl_name = XFS_FILESTREAM_TIMER,
.procname = "filestream_centisecs",
.data = &xfs_params.fstrm_timer.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &xfs_params.fstrm_timer.min,
.extra2 = &xfs_params.fstrm_timer.max,
},
/* please keep this the last entry */
#ifdef CONFIG_PROC_FS
{
- .ctl_name = XFS_STATS_CLEAR,
.procname = "stats_clear",
.data = &xfs_params.stats_clear.val,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &xfs_stats_clear_proc_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = xfs_stats_clear_proc_handler,
.extra1 = &xfs_params.stats_clear.min,
.extra2 = &xfs_params.stats_clear.max
},
@@ -229,7 +199,6 @@ static ctl_table xfs_table[] = {
static ctl_table xfs_dir_table[] = {
{
- .ctl_name = FS_XFS,
.procname = "xfs",
.mode = 0555,
.child = xfs_table
@@ -239,7 +208,6 @@ static ctl_table xfs_dir_table[] = {
static ctl_table xfs_root_table[] = {
{
- .ctl_name = CTL_FS,
.procname = "fs",
.mode = 0555,
.child = xfs_dir_table
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index ad7fbead4c97..00cabf5354d2 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -36,7 +36,6 @@ struct attrlist_cursor_kern;
/*
* 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 */