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 472525eff14c08e18acccef5963d0477d8a006f5..06892dc58be21c24c6a036236667a6b90e3a8876 100644 (file)
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -991,6 +991,48 @@ static ssize_t aio_setup_single_vector(int rw, 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
@@ -1042,6 +1084,14 @@ rw_common:
                ret = aio_rw_vect_retry(req, rw, rw_op);
                break;
 
+       case IOCB_CMD_READ_ITER:
+               ret = aio_read_iter(req, req->ki_iter);
+               break;
+
+       case IOCB_CMD_WRITE_ITER:
+               ret = aio_write_iter(req, req->ki_iter);
+               break;
+
        case IOCB_CMD_FDSYNC:
                if (!file->f_op->aio_fsync)
                        return -EINVAL;
@@ -1144,6 +1194,7 @@ int aio_kernel_submit(struct kiocb *iocb, unsigned short op, void *ptr)
 
        iocb->ki_opcode = op;
        iocb->ki_buf = (char __user *)(unsigned long)ptr;
+       iocb->ki_iter = ptr;
 
        ret = aio_run_iocb(iocb, 0);
 

diff --git a/include/linux/aio.h b/include/linux/aio.h
index bf2642b753fd6839da7c32a77a4128a85de79726..2bb87b52cb74a6a2f4ff5d7e2474ebf7a5342344 100644 (file)
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -66,6 +66,7 @@ struct kiocb {
         * this is the underlying eventfd context to deliver events to.
         */
        struct eventfd_ctx      *ki_eventfd;
+       struct iov_iter         *ki_iter;
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)

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,
 };
 
 /*