[PATCH] Add vector AIO support

This work is initially done by Zach Brown to add support for vectored aio.
These are the core changes for AIO to support
IOCB_CMD_PREADV/IOCB_CMD_PWRITEV.

[akpm@osdl.org: huge build fix]
Signed-off-by: Zach Brown <zach.brown@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Acked-by: Benjamin LaHaise <bcrl@kvack.org>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 117 insertions, 54 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 27ff56540c73..2e0d1505ee36 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -415,6 +415,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx)
 	req->ki_retry = NULL;
 	req->ki_dtor = NULL;
 	req->private = NULL;
+	req->ki_iovec = NULL;
 	INIT_LIST_HEAD(&req->ki_run_list);
 
 	/* Check if the completion queue has enough free space to
@@ -460,6 +461,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 
 	if (req->ki_dtor)
 		req->ki_dtor(req);
+	if (req->ki_iovec != &req->ki_inline_vec)
+		kfree(req->ki_iovec);
 	kmem_cache_free(kiocb_cachep, req);
 	ctx->reqs_active--;
 
@@ -1301,69 +1304,63 @@ asmlinkage long sys_io_destroy(aio_context_t ctx)
 	return -EINVAL;
 }
 
-/*
- * aio_p{read,write} are the default  ki_retry methods for
- * IO_CMD_P{READ,WRITE}.  They maintains kiocb retry state around potentially
- * multiple calls to f_op->aio_read().  They loop around partial progress
- * instead of returning -EIOCBRETRY because they don't have the means to call
- * kick_iocb().
- */
-static ssize_t aio_pread(struct kiocb *iocb)
+static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret)
 {
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	ssize_t ret = 0;
-
-	do {
-		iocb->ki_inline_vec.iov_base = iocb->ki_buf;
-		iocb->ki_inline_vec.iov_len = iocb->ki_left;
-
-		ret = file->f_op->aio_read(iocb, &iocb->ki_inline_vec,
-						1, iocb->ki_pos);
-		/*
-		 * Can't just depend on iocb->ki_left to determine
-		 * whether we are done. This may have been a short read.
-		 */
-		if (ret > 0) {
-			iocb->ki_buf += ret;
-			iocb->ki_left -= ret;
+	struct iovec *iov = &iocb->ki_iovec[iocb->ki_cur_seg];
+
+	BUG_ON(ret <= 0);
+
+	while (iocb->ki_cur_seg < iocb->ki_nr_segs && ret > 0) {
+		ssize_t this = min((ssize_t)iov->iov_len, ret);
+		iov->iov_base += this;
+		iov->iov_len -= this;
+		iocb->ki_left -= this;
+		ret -= this;
+		if (iov->iov_len == 0) {
+			iocb->ki_cur_seg++;
+			iov++;
 		}
+	}
 
-		/*
-		 * For pipes and sockets we return once we have some data; for
-		 * regular files we retry till we complete the entire read or
-		 * find that we can't read any more data (e.g short reads).
-		 */
-	} while (ret > 0 && iocb->ki_left > 0 &&
-		 !S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode));
-
-	/* This means we must have transferred all that we could */
-	/* No need to retry anymore */
-	if ((ret == 0) || (iocb->ki_left == 0))
-		ret = iocb->ki_nbytes - iocb->ki_left;
-
-	return ret;
+	/* the caller should not have done more io than what fit in
+	 * the remaining iovecs */
+	BUG_ON(ret > 0 && iocb->ki_left == 0);
 }
 
-/* see aio_pread() */
-static ssize_t aio_pwrite(struct kiocb *iocb)
+static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
 {
 	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	ssize_t (*rw_op)(struct kiocb *, const struct iovec *,
+			 unsigned long, loff_t);
 	ssize_t ret = 0;
+	unsigned short opcode;
+
+	if ((iocb->ki_opcode == IOCB_CMD_PREADV) ||
+		(iocb->ki_opcode == IOCB_CMD_PREAD)) {
+		rw_op = file->f_op->aio_read;
+		opcode = IOCB_CMD_PREADV;
+	} else {
+		rw_op = file->f_op->aio_write;
+		opcode = IOCB_CMD_PWRITEV;
+	}
 
 	do {
-		iocb->ki_inline_vec.iov_base = iocb->ki_buf;
-		iocb->ki_inline_vec.iov_len = iocb->ki_left;
-
-		ret = file->f_op->aio_write(iocb, &iocb->ki_inline_vec,
-						1, iocb->ki_pos);
-		if (ret > 0) {
-			iocb->ki_buf += ret;
-			iocb->ki_left -= ret;
-		}
-	} while (ret > 0 && iocb->ki_left > 0);
+		ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg],
+			    iocb->ki_nr_segs - iocb->ki_cur_seg,
+			    iocb->ki_pos);
+		if (ret > 0)
+			aio_advance_iovec(iocb, ret);
+
+	/* retry all partial writes.  retry partial reads as long as its a
+	 * regular file. */
+	} while (ret > 0 && iocb->ki_left > 0 &&
+		 (opcode == IOCB_CMD_PWRITEV ||
+		  (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode))));
 
+	/* This means we must have transferred all that we could */
+	/* No need to retry anymore */
 	if ((ret == 0) || (iocb->ki_left == 0))
 		ret = iocb->ki_nbytes - iocb->ki_left;
 
@@ -1390,6 +1387,38 @@ static ssize_t aio_fsync(struct kiocb *iocb)
 	return ret;
 }
 
+static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb)
+{
+	ssize_t ret;
+
+	ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf,
+				    kiocb->ki_nbytes, 1,
+				    &kiocb->ki_inline_vec, &kiocb->ki_iovec);
+	if (ret < 0)
+		goto out;
+
+	kiocb->ki_nr_segs = kiocb->ki_nbytes;
+	kiocb->ki_cur_seg = 0;
+	/* ki_nbytes/left now reflect bytes instead of segs */
+	kiocb->ki_nbytes = ret;
+	kiocb->ki_left = ret;
+
+	ret = 0;
+out:
+	return ret;
+}
+
+static ssize_t aio_setup_single_vector(struct kiocb *kiocb)
+{
+	kiocb->ki_iovec = &kiocb->ki_inline_vec;
+	kiocb->ki_iovec->iov_base = kiocb->ki_buf;
+	kiocb->ki_iovec->iov_len = kiocb->ki_left;
+	kiocb->ki_nr_segs = 1;
+	kiocb->ki_cur_seg = 0;
+	kiocb->ki_nbytes = kiocb->ki_left;
+	return 0;
+}
+
 /*
  * aio_setup_iocb:
  *	Performs the initial checks and aio retry method
@@ -1412,9 +1441,12 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb)
 		ret = security_file_permission(file, MAY_READ);
 		if (unlikely(ret))
 			break;
+		ret = aio_setup_single_vector(kiocb);
+		if (ret)
+			break;
 		ret = -EINVAL;
 		if (file->f_op->aio_read)
-			kiocb->ki_retry = aio_pread;
+			kiocb->ki_retry = aio_rw_vect_retry;
 		break;
 	case IOCB_CMD_PWRITE:
 		ret = -EBADF;
@@ -1427,9 +1459,40 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb)
 		ret = security_file_permission(file, MAY_WRITE);
 		if (unlikely(ret))
 			break;
+		ret = aio_setup_single_vector(kiocb);
+		if (ret)
+			break;
+		ret = -EINVAL;
+		if (file->f_op->aio_write)
+			kiocb->ki_retry = aio_rw_vect_retry;
+		break;
+	case IOCB_CMD_PREADV:
+		ret = -EBADF;
+		if (unlikely(!(file->f_mode & FMODE_READ)))
+			break;
+		ret = security_file_permission(file, MAY_READ);
+		if (unlikely(ret))
+			break;
+		ret = aio_setup_vectored_rw(READ, kiocb);
+		if (ret)
+			break;
+		ret = -EINVAL;
+		if (file->f_op->aio_read)
+			kiocb->ki_retry = aio_rw_vect_retry;
+		break;
+	case IOCB_CMD_PWRITEV:
+		ret = -EBADF;
+		if (unlikely(!(file->f_mode & FMODE_WRITE)))
+			break;
+		ret = security_file_permission(file, MAY_WRITE);
+		if (unlikely(ret))
+			break;
+		ret = aio_setup_vectored_rw(WRITE, kiocb);
+		if (ret)
+			break;
 		ret = -EINVAL;
 		if (file->f_op->aio_write)
-			kiocb->ki_retry = aio_pwrite;
+			kiocb->ki_retry = aio_rw_vect_retry;
 		break;
 	case IOCB_CMD_FDSYNC:
 		ret = -EINVAL;