ocfs2: nowait aio support (c4c2416a) · Commits · 戴 / test

fs/ocfs2/dir.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -1958,7 +1958,7 @@ int ocfs2_readdir(struct file file, struct dir_context ctx)

		trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno);

		error = ocfs2_inode_lock_atime(inode, file->f_path.mnt, &lock_level);
		error = ocfs2_inode_lock_atime(inode, file->f_path.mnt, &lock_level, 1);
		if (lock_level && error >= 0) {
		/* We release EX lock which used to update atime
		* and get PR lock again to reduce contention

fs/ocfs2/dlmglue.c

+15 −5

Original line number	Diff line number	Diff line
		@@ -2546,12 +2546,17 @@ int ocfs2_inode_lock_with_page(struct inode *inode,

		int ocfs2_inode_lock_atime(struct inode *inode,
		struct vfsmount *vfsmnt,
		int *level)
		int *level, int wait)
		{
		int ret;

		if (wait)
		ret = ocfs2_inode_lock(inode, NULL, 0);
		else
		ret = ocfs2_try_inode_lock(inode, NULL, 0);

		if (ret < 0) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		return ret;
		}
		@@ -2564,8 +2569,13 @@ int ocfs2_inode_lock_atime(struct inode *inode,
		struct buffer_head *bh = NULL;

		ocfs2_inode_unlock(inode, 0);
		if (wait)
		ret = ocfs2_inode_lock(inode, &bh, 1);
		else
		ret = ocfs2_try_inode_lock(inode, &bh, 1);

		if (ret < 0) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		return ret;
		}

fs/ocfs2/dlmglue.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -146,7 +146,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write);
		void ocfs2_open_unlock(struct inode *inode);
		int ocfs2_inode_lock_atime(struct inode *inode,
		struct vfsmount *vfsmnt,
		int *level);
		int *level, int wait);
		int ocfs2_inode_lock_full_nested(struct inode *inode,
		struct buffer_head **ret_bh,
		int ex,

fs/ocfs2/file.c

+80 −21

Original line number	Diff line number	Diff line
		@@ -140,6 +140,8 @@ static int ocfs2_file_open(struct inode inode, struct file file)
		spin_unlock(&oi->ip_lock);
		}

		file->f_mode \|= FMODE_NOWAIT;

		leave:
		return status;
		}
		@@ -2132,12 +2134,12 @@ out:
		}

		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 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
		* if we need to make modifications here.
		*/
		for(;;) {
		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;
		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 @@ static int ocfs2_prepare_inode_for_write(struct file *file,

		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 @@ out:
		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 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
		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,
		@@ -2230,11 +2263,16 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
		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;

		if (nowait) {
		if (!inode_trylock(inode))
		return -EAGAIN;
		} else
		inode_lock(inode);

		/*
		@@ -2244,8 +2282,12 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
		*/
		rw_level = (!direct_io \|\| full_coherency \|\| append_write);

		if (nowait)
		ret = ocfs2_try_rw_lock(inode, rw_level);
		else
		ret = ocfs2_rw_lock(inode, rw_level);
		if (ret < 0) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		goto out_mutex;
		}
		@@ -2260,8 +2302,12 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
		* other nodes to drop their caches. Buffered I/O
		* already does this in write_begin().
		*/
		if (nowait)
		ret = ocfs2_try_inode_lock(inode, NULL, 1);
		else
		ret = ocfs2_inode_lock(inode, NULL, 1);
		if (ret < 0) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		goto out;
		}
		@@ -2277,8 +2323,9 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
		}
		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) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		goto out;
		}
		@@ -2355,6 +2402,8 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
		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,
		@@ -2369,13 +2418,21 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
		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) {
		if (direct_io) {
		if (nowait)
		ret = ocfs2_try_rw_lock(inode, 0);
		else
		ret = ocfs2_rw_lock(inode, 0);

		if (ret < 0) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		goto bail;
		}
		@@ -2393,8 +2450,10 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
		* 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) {
		if (ret != -EAGAIN)
		mlog_errno(ret);
		goto bail;
		}

fs/ocfs2/mmap.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -184,7 +184,7 @@ int ocfs2_mmap(struct file file, struct vm_area_struct vma)
		int ret = 0, lock_level = 0;

		ret = ocfs2_inode_lock_atime(file_inode(file),
		file->f_path.mnt, &lock_level);
		file->f_path.mnt, &lock_level, 1);
		if (ret < 0) {
		mlog_errno(ret);
		goto out;

Admin message