ocfs2: nowait aio support
Return EAGAIN if any of the following checks fail for direct I/O:
- Cannot get the related locks immediately
- Blocks are not allocated at the write location, it will trigger block
allocation and block IO operations.
[ghe@suse.com: v4]
Link: http://lkml.kernel.org/r/1516007283-29932-4-git-send-email-ghe@suse.com
[ghe@suse.com: v2]
Link: http://lkml.kernel.org/r/1511944612-9629-4-git-send-email-ghe@suse.com
Link: http://lkml.kernel.org/r/1511775987-841-4-git-send-email-ghe@suse.com
Signed-off-by: Gang He <ghe@suse.com>
Reviewed-by: Alex Chen <alex.chen@huawei.com>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <ge.changwei@h3c.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index a1d0510..5d1784a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -140,6 +140,8 @@
spin_unlock(&oi->ip_lock);
}
+ file->f_mode |= FMODE_NOWAIT;
+
leave:
return status;
}
@@ -2132,12 +2134,12 @@
}
static int ocfs2_prepare_inode_for_write(struct file *file,
- loff_t pos,
- size_t count)
+ loff_t pos, size_t count, int wait)
{
- int ret = 0, meta_level = 0;
+ int ret = 0, meta_level = 0, overwrite_io = 0;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = d_inode(dentry);
+ struct buffer_head *di_bh = NULL;
loff_t end;
/*
@@ -2145,13 +2147,40 @@
* if we need to make modifications here.
*/
for(;;) {
- ret = ocfs2_inode_lock(inode, NULL, meta_level);
+ if (wait)
+ ret = ocfs2_inode_lock(inode, NULL, meta_level);
+ else
+ ret = ocfs2_try_inode_lock(inode,
+ overwrite_io ? NULL : &di_bh, meta_level);
if (ret < 0) {
meta_level = -1;
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out;
}
+ /*
+ * Check if IO will overwrite allocated blocks in case
+ * IOCB_NOWAIT flag is set.
+ */
+ if (!wait && !overwrite_io) {
+ overwrite_io = 1;
+ if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+
+ ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
+ brelse(di_bh);
+ di_bh = NULL;
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+ if (ret < 0) {
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
+ goto out_unlock;
+ }
+ }
+
/* Clear suid / sgid if necessary. We do this here
* instead of later in the write path because
* remove_suid() calls ->setattr without any hint that
@@ -2199,7 +2228,9 @@
out_unlock:
trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
- pos, count);
+ pos, count, wait);
+
+ brelse(di_bh);
if (meta_level >= 0)
ocfs2_inode_unlock(inode, meta_level);
@@ -2211,7 +2242,7 @@
static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
- int direct_io, rw_level;
+ int rw_level;
ssize_t written = 0;
ssize_t ret;
size_t count = iov_iter_count(from);
@@ -2223,6 +2254,8 @@
void *saved_ki_complete = NULL;
int append_write = ((iocb->ki_pos + count) >=
i_size_read(inode) ? 1 : 0);
+ int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
+ int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2230,12 +2263,17 @@
file->f_path.dentry->d_name.name,
(unsigned int)from->nr_segs); /* GRRRRR */
+ if (!direct_io && nowait)
+ return -EOPNOTSUPP;
+
if (count == 0)
return 0;
- direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
-
- inode_lock(inode);
+ if (nowait) {
+ if (!inode_trylock(inode))
+ return -EAGAIN;
+ } else
+ inode_lock(inode);
/*
* Concurrent O_DIRECT writes are allowed with
@@ -2244,9 +2282,13 @@
*/
rw_level = (!direct_io || full_coherency || append_write);
- ret = ocfs2_rw_lock(inode, rw_level);
+ if (nowait)
+ ret = ocfs2_try_rw_lock(inode, rw_level);
+ else
+ ret = ocfs2_rw_lock(inode, rw_level);
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out_mutex;
}
@@ -2260,9 +2302,13 @@
* other nodes to drop their caches. Buffered I/O
* already does this in write_begin().
*/
- ret = ocfs2_inode_lock(inode, NULL, 1);
+ if (nowait)
+ ret = ocfs2_try_inode_lock(inode, NULL, 1);
+ else
+ ret = ocfs2_inode_lock(inode, NULL, 1);
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out;
}
@@ -2277,9 +2323,10 @@
}
count = ret;
- ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count);
+ ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, !nowait);
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out;
}
@@ -2355,6 +2402,8 @@
int ret = 0, rw_level = -1, lock_level = 0;
struct file *filp = iocb->ki_filp;
struct inode *inode = file_inode(filp);
+ int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
+ int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2369,14 +2418,22 @@
goto bail;
}
+ if (!direct_io && nowait)
+ return -EOPNOTSUPP;
+
/*
* buffered reads protect themselves in ->readpage(). O_DIRECT reads
* need locks to protect pending reads from racing with truncate.
*/
- if (iocb->ki_flags & IOCB_DIRECT) {
- ret = ocfs2_rw_lock(inode, 0);
+ if (direct_io) {
+ if (nowait)
+ ret = ocfs2_try_rw_lock(inode, 0);
+ else
+ ret = ocfs2_rw_lock(inode, 0);
+
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto bail;
}
rw_level = 0;
@@ -2393,9 +2450,11 @@
* like i_size. This allows the checks down below
* generic_file_aio_read() a chance of actually working.
*/
- ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level);
+ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
+ !nowait);
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto bail;
}
ocfs2_inode_unlock(inode, lock_level);