IO-Uring Archive on lore.kernel.org
 help / color / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: io-uring@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 9/9] io_uring: add IORING_OP_MADVISE
Date: Sat, 28 Dec 2019 12:21:18 -0700
Message-ID: <20191228192118.4005-10-axboe@kernel.dk> (raw)
In-Reply-To: <20191228192118.4005-1-axboe@kernel.dk>

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@kernel.dk>
---
 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 8d99b9c5a568..b1f28037aa74 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_LAST] = {
 		/* IORING_OP_FADVISE */
 		.needs_file		= 1,
 	},
+	{
+		/* IORING_OP_MADVISE */
+		.needs_mm		= 1,
+	},
 };
 
 static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -2446,6 +2453,42 @@ 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)
+	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)
+	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 defined(CONFIG_ADVISE_SYSCALLS)
@@ -3775,6 +3818,9 @@ 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);
@@ -3979,6 +4025,14 @@ 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


      parent reply index

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-28 19:21 [PATCHSET 0/9] cleanups, improvements, additions Jens Axboe
2019-12-28 19:21 ` [PATCH 1/9] io_uring: remove two unnecessary function declarations Jens Axboe
2019-12-28 19:21 ` [PATCH 2/9] io_uring: add lookup table for various opcode needs Jens Axboe
2019-12-28 19:21 ` [PATCH 3/9] io_uring: split overflow state into SQ and CQ side Jens Axboe
2019-12-28 19:21 ` [PATCH 4/9] io_uring: improve poll completion performance Jens Axboe
2019-12-28 19:21 ` [PATCH 5/9] io_uring: add non-vectored read/write commands Jens Axboe
2019-12-28 19:21 ` [PATCH 6/9] io_uring: allow use of offset == -1 to mean file position Jens Axboe
2019-12-28 19:21 ` [PATCH 7/9] io_uring: add IORING_OP_FADVISE Jens Axboe
2019-12-28 19:21 ` [PATCH 8/9] mm: make do_madvise() available internally Jens Axboe
2019-12-28 19:21 ` Jens Axboe [this message]

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191228192118.4005-10-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

IO-Uring Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/io-uring/0 io-uring/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 io-uring io-uring/ https://lore.kernel.org/io-uring \
		io-uring@vger.kernel.org
	public-inbox-index io-uring

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.io-uring


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git