[PATCH 3/3] io_uring: add IORING_OP_MADVISE

[Jens Axboe <axboe@xxxxxxxxx>]

This adds support for doing madvise(2) through io_uring. We assume that
any operation can block, and hence punt everything async. This could be
improved, but hard to make bullet proof. The async punt ensures it's
safe.

Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
 fs/io_uring.c                 | 56 ++++++++++++++++++++++++++++++++++-
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0b200a7d4ae0..378f97cc2bf2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -403,7 +403,10 @@ struct io_files_update {
 
 struct io_fadvise {
 	struct file			*file;
-	u64				offset;
+	union {
+		u64			offset;
+		u64			addr;
+	};
 	u32				len;
 	u32				advice;
 };
@@ -682,6 +685,10 @@ static const struct io_op_def io_op_defs[] = {
 		/* IORING_OP_FADVISE */
 		.needs_file		= 1,
 	},
+	{
+		/* IORING_OP_MADVISE */
+		.needs_mm		= 1,
+	},
 };
 
 static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -2448,6 +2455,42 @@ static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
 	return 0;
 }
 
+static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	if (sqe->ioprio || sqe->buf_index || sqe->off)
+		return -EINVAL;
+
+	req->fadvise.addr = READ_ONCE(sqe->addr);
+	req->fadvise.len = READ_ONCE(sqe->len);
+	req->fadvise.advice = READ_ONCE(sqe->fadvise_advice);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_fadvise *fa = &req->fadvise;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	ret = do_madvise(fa->addr, fa->len, fa->advice);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	if (sqe->ioprio || sqe->buf_index || sqe->addr)
@@ -3769,6 +3812,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	case IORING_OP_FADVISE:
 		ret = io_fadvise_prep(req, sqe);
 		break;
+	case IORING_OP_MADVISE:
+		ret = io_madvise_prep(req, sqe);
+		break;
 	default:
 		printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
 				req->opcode);
@@ -3973,6 +4019,14 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		}
 		ret = io_fadvise(req, nxt, force_nonblock);
 		break;
+	case IORING_OP_MADVISE:
+		if (sqe) {
+			ret = io_madvise_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_madvise(req, nxt, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index f87d8fb42916..7cb6fe0fccd7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -88,6 +88,7 @@ enum {
 	IORING_OP_READ,
 	IORING_OP_WRITE,
 	IORING_OP_FADVISE,
+	IORING_OP_MADVISE,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
2.24.1