[04/10] fs: Introduce RWF_NOWAIT
diff mbox

Message ID 20170606111939.27272-5-rgoldwyn@suse.de
State New
Headers show

Commit Message

Goldwyn Rodrigues June 6, 2017, 11:19 a.m. UTC
From: Goldwyn Rodrigues <rgoldwyn@suse.com>

RWF_NOWAIT informs kernel to bail out if an AIO request will block
for reasons such as file allocations, or a writeback triggered,
or would block while allocating requests while performing
direct I/O.

RWF_NOWAIT is translated to IOCB_NOWAIT for iocb->ki_flags.

The check for -EOPNOTSUPP is placed in generic_file_write_iter(). This
is called by most filesystems, either through fsops.write_iter() or through
the function defined by write_iter(). If not, we perform the check defined
by .write_iter() which is called for direct IO specifically.

Filesystems xfs, btrfs and ext4 would be supported in the following patches.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/9p/vfs_file.c        | 3 +++
 fs/aio.c                | 6 ++++++
 fs/ceph/file.c          | 3 +++
 fs/cifs/file.c          | 3 +++
 fs/fuse/file.c          | 3 +++
 fs/nfs/direct.c         | 3 +++
 fs/ocfs2/file.c         | 3 +++
 include/linux/fs.h      | 5 ++++-
 include/uapi/linux/fs.h | 1 +
 mm/filemap.c            | 3 +++
 10 files changed, 32 insertions(+), 1 deletion(-)

Comments

Al Viro June 10, 2017, 5:27 a.m. UTC | #1
On Tue, Jun 06, 2017 at 06:19:33AM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> RWF_NOWAIT informs kernel to bail out if an AIO request will block
> for reasons such as file allocations, or a writeback triggered,
> or would block while allocating requests while performing
> direct I/O.
> 
> RWF_NOWAIT is translated to IOCB_NOWAIT for iocb->ki_flags.
> 
> The check for -EOPNOTSUPP is placed in generic_file_write_iter(). This
> is called by most filesystems, either through fsops.write_iter() or through
> the function defined by write_iter(). If not, we perform the check defined
> by .write_iter() which is called for direct IO specifically.
> 
> Filesystems xfs, btrfs and ext4 would be supported in the following patches.

Umm...  What about ->write_iter() instances outside of fs/*?  Even in fs/*,
consider e.g.
int cifs_get_writer(struct cifsInodeInfo *cinode)
{
        int rc;

start:
        rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK,
                         TASK_KILLABLE);

and cifs_file_write_iter() calling it before going to generic_file_write_iter().
Ditto for cifs_struct_writev()...  coda_file_write_iter() does inode_lock()
before calling vfs_iter_write().  ext2_dax_write_iter(): inode_lock().
f2fs_file_write_iter(): ditto.  fuse_file_write_iter(): ditto in case when
->writeback_cache is false.  gfs2 is O_APPEND case: almost certainly blocks.
ncp_file_write_iter(): blocks (mutex_lock(&NCP_FINFO(inode)->open_mutex)
in ncp_make_open(), not to mention anything else). ntfs_file_write_iter():
inode_lock().  orangefs_file_write_iter(): ditto.  ubifs_write_iter():
may block in update_mctime().  udf_file_write_iter(): inode_lock().

Lustre sure as hell does block before it gets anywhere near mm/filemap.c.

And that - just from looking at regular files.  Then we have sockets and
pipes, not to mention weird stuff like fs/fuse/cuse.c, etc.
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch
diff mbox

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3de3b4a89d89..403681db7723 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -411,6 +411,9 @@  v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	loff_t origin;
 	int err = 0;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	retval = generic_write_checks(iocb, from);
 	if (retval <= 0)
 		return retval;
diff --git a/fs/aio.c b/fs/aio.c
index 020fa0045e3c..34027b67e2f4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1592,6 +1592,12 @@  static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		goto out_put_req;
 	}
 
+	if ((req->common.ki_flags & IOCB_NOWAIT) &&
+			!(req->common.ki_flags & IOCB_DIRECT)) {
+		ret = -EOPNOTSUPP;
+		goto out_put_req;
+	}
+
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
 	if (unlikely(ret)) {
 		pr_debug("EFAULT: aio_key\n");
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 29308a80d66f..366b0bb71f97 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1300,6 +1300,9 @@  static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int err, want, got;
 	loff_t pos;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0fd081bd2a2f..ff84fa9ddb6c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2725,6 +2725,9 @@  ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
 	 * write request.
 	 */
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	rc = generic_write_checks(iocb, from);
 	if (rc <= 0)
 		return rc;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3ee4fdc3da9e..812c7bd0c290 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1425,6 +1425,9 @@  static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	ssize_t res;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	if (is_bad_inode(inode))
 		return -EIO;
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 6fb9fad2d1e6..c8e7dd76126c 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -979,6 +979,9 @@  ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 	dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
 		file, iov_iter_count(iter), (long long) iocb->ki_pos);
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	result = generic_write_checks(iocb, iter);
 	if (result <= 0)
 		return result;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index bfeb647459d9..e7f8ba890305 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2235,6 +2235,9 @@  static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (count == 0)
 		return 0;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 
 	inode_lock(inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dc0ab585cd56..2a7d14af6d12 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -268,6 +268,7 @@  struct writeback_control;
 #define IOCB_DSYNC		(1 << 4)
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
+#define IOCB_NOWAIT		(1 << 7)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -3060,7 +3061,7 @@  static inline int iocb_flags(struct file *file)
 
 static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
 {
-	if (unlikely(flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)))
+	if (unlikely(flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT)))
 		return -EOPNOTSUPP;
 
 	if (flags & RWF_HIPRI)
@@ -3069,6 +3070,8 @@  static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
 		ki->ki_flags |= IOCB_DSYNC;
 	if (flags & RWF_SYNC)
 		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	if (flags & RWF_NOWAIT)
+		ki->ki_flags |= IOCB_NOWAIT;
 	return 0;
 }
 
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 24e61a54feaa..29969fb7f9a7 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -360,5 +360,6 @@  struct fscrypt_key {
 #define RWF_HIPRI			0x00000001 /* high priority request, poll if possible */
 #define RWF_DSYNC			0x00000002 /* per-IO O_DSYNC */
 #define RWF_SYNC			0x00000004 /* per-IO O_SYNC */
+#define RWF_NOWAIT			0x00000008 /* per-IO, return -EAGAIN if operation would block */
 
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/mm/filemap.c b/mm/filemap.c
index 87aba7698584..097213275461 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3006,6 +3006,9 @@  ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0)