aio: add aio support for iov_iter arguments

This adds iocb cmds which specify that memory is held in iov_iter
structures.  This lets kernel callers specify memory that can be
expressed in an iov_iter, which includes pages in bio_vec arrays.

Only kernel callers can provide an iov_iter so it doesn't make a lot of
sense to expose the IOCB_CMD values for this as part of the user space
ABI.

But kernel callers should also be able to perform the usual aio
operations which suggests using the the existing operation namespace and
support code.

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Zach Brown <zab@zabbo.net>

diff --git a/fs/aio.c b/fs/aio.c
index 8e700bacac78daf84336a6cbd12194be9dc91a1e..8e46c05ce87a3a912d8edebedac55a681a691af9 100644 (file)
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1177,13 +1177,55 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
        return 0;
 }
 
+static ssize_t aio_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+       struct file *file = iocb->ki_filp;
+       ssize_t ret;
+
+       if (unlikely(!is_kernel_kiocb(iocb)))
+               return -EINVAL;
+
+       if (unlikely(!(file->f_mode & FMODE_READ)))
+               return -EBADF;
+
+       ret = security_file_permission(file, MAY_READ);
+       if (unlikely(ret))
+               return ret;
+
+       if (!file->f_op->read_iter)
+               return -EINVAL;
+
+       return file->f_op->read_iter(iocb, iter, iocb->ki_pos);
+}
+
+static ssize_t aio_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+       struct file *file = iocb->ki_filp;
+       ssize_t ret;
+
+       if (unlikely(!is_kernel_kiocb(iocb)))
+               return -EINVAL;
+
+       if (unlikely(!(file->f_mode & FMODE_WRITE)))
+               return -EBADF;
+
+       ret = security_file_permission(file, MAY_WRITE);
+       if (unlikely(ret))
+               return ret;
+
+       if (!file->f_op->write_iter)
+               return -EINVAL;
+
+       return file->f_op->write_iter(iocb, iter, iocb->ki_pos);
+}
+
 /*
  * aio_setup_iocb:
  *     Performs the initial checks and aio retry method
  *     setup for the kiocb at the time of io submission.
  */
 static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
-                           char __user *buf, bool compat)
+                           void *buf, bool compat)
 {
        struct file *file = req->ki_filp;
        ssize_t ret;
@@ -1248,6 +1290,14 @@ rw_common:
                        file_end_write(file);
                break;
 
+       case IOCB_CMD_READ_ITER:
+               ret = aio_read_iter(req, buf);
+               break;
+
+       case IOCB_CMD_WRITE_ITER:
+               ret = aio_write_iter(req, buf);
+               break;
+
        case IOCB_CMD_FDSYNC:
                if (!file->f_op->aio_fsync)
                        return -EINVAL;
@@ -1418,7 +1468,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
        req->ki_nbytes = iocb->aio_nbytes;
 
        ret = aio_run_iocb(req, iocb->aio_lio_opcode,
-                          (char __user *)(unsigned long)iocb->aio_buf,
+                          (void *)(unsigned long)iocb->aio_buf,
                           compat);
        if (ret)
                goto out_put_req;

diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index bb2554f7fbd12a677015d48703ccf681357e84c6..22ce4bd2501322a6beb468ed84168ebcda774a8b 100644 (file)
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -44,6 +44,8 @@ enum {
        IOCB_CMD_NOOP = 6,
        IOCB_CMD_PREADV = 7,
        IOCB_CMD_PWRITEV = 8,
+       IOCB_CMD_READ_ITER = 9,
+       IOCB_CMD_WRITE_ITER = 10,
 };
 
 /*