[PATCH 2/8] nowait aio: Introduce RWF_NOWAIT
From: Goldwyn Rodrigues <hidden>
Date: 2017-05-09 12:22:32
Also in:
linux-api, linux-btrfs, linux-ext4, linux-fsdevel, linux-xfs
Subsystem:
9p file system, aio, ceph distributed file system client (ceph), filesystems (vfs and infrastructure), fuse filesystem [core], memory management, nfs, sunrpc, and lockd clients, oracle cluster filesystem 2 (ocfs2), page cache, the rest · Maintainers:
Eric Van Hensbergen, Latchesar Ionkov, Dominique Martinet, Benjamin LaHaise, Ilya Dryomov, Alex Markuze, Viacheslav Dubeyko, Alexander Viro, Christian Brauner, Miklos Szeredi, Andrew Morton, Trond Myklebust, Anna Schumaker, Mark Fasheh, Joel Becker, Joseph Qi, Matthew Wilcox, Linus Torvalds
From: Goldwyn Rodrigues <redacted> This flag 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. Unfortunately, aio_flags is not checked for validity, which would break existing applications which have it set to anything besides zero or IOCB_FLAG_RESFD. So, we are using aio_reserved1 and renaming it to aio_rw_flags. 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. Signed-off-by: Goldwyn Rodrigues <redacted> --- 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(-)
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..ea9f8581d902 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 26cc95421cca..af28419b1731 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c@@ -1267,6 +1267,9 @@ 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 21d404535739..f8858a06e119 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c@@ -2638,6 +2638,9 @@ 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 ec238fb5a584..72786e798319 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 c1b5fed7c863..dcea0caa5cb5 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c@@ -996,6 +996,9 @@ 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 869c9a6fe58d..4cb62e032b70 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h@@ -270,6 +270,7 @@ 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;
@@ -3051,7 +3052,7 @@ 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)
@@ -3060,6 +3061,8 @@ 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 048a85e9f017..7bcaef101876 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h@@ -347,5 +347,6 @@ struct fscrypt_policy { #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 1694623a6289..d51670b7fe6b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c@@ -2982,6 +2982,9 @@ 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)
--
2.12.0