Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     "David S . Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        Willem de Bruijn <willemb@google.com>,
        Jens Axboe <axboe@kernel.dk>, kernel-team@fb.com,
        Pavel Begunkov <asml.silence@gmail.com>
Subject: [RFC net-next v3 20/29] io_uring: add zc notification flush requests
Date:   Tue, 28 Jun 2022 19:56:42 +0100
Message-Id: <dcde76fb17478a0555771647105e57ee7b1b12bf.1653992701.git.asml.silence@gmail.com>
In-Reply-To: <cover.1653992701.git.asml.silence@gmail.com>
References: <cover.1653992701.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Overlay notification control onto IORING_OP_RSRC_UPDATE (former
IORING_OP_FILES_UPDATE). It allows to flush a range of zc notifications
from slots with indexes [sqe->off, sqe->off+sqe->len). If sqe->arg is
not zero, it also copies sqe->arg as a new tag for all flushed
notifications.

Note, it doesn't flush a notification of a slot if there was no requests
attached to it (since last flush or registration).

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c                 | 47 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 48 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e9fc7e076c7f..a88c9c73ed1d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1284,6 +1284,7 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_RSRC_UPDATE] = {
 		.audit_skip		= 1,
 		.iopoll			= 1,
+		.ioprio			= 1,
 	},
 	[IORING_OP_STATX] = {
 		.audit_skip		= 1,
@@ -2953,6 +2954,16 @@ static void io_notif_slot_flush(struct io_notif_slot *slot)
 		io_notif_complete(notif);
 }
 
+static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot,
+					      unsigned int issue_flags)
+{
+	if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+		slot->notif->task = current;
+		io_get_task_refs(1);
+	}
+	io_notif_slot_flush(slot);
+}
+
 static __cold int io_notif_unregister(struct io_ring_ctx *ctx)
 	__must_hold(&ctx->uring_lock)
 {
@@ -8286,6 +8297,40 @@ static int io_rsrc_update_prep(struct io_kiocb *req,
 	return 0;
 }
 
+static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	unsigned len = req->rsrc_update.nr_args;
+	unsigned idx_end, idx = req->rsrc_update.offset;
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	if (unlikely(check_add_overflow(idx, len, &idx_end))) {
+		ret = -EOVERFLOW;
+		goto out;
+	}
+	if (unlikely(idx_end > ctx->nr_notif_slots)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (; idx < idx_end; idx++) {
+		struct io_notif_slot *slot = &ctx->notif_slots[idx];
+
+		if (!slot->notif)
+			continue;
+		if (req->rsrc_update.arg)
+			slot->tag = req->rsrc_update.arg;
+		io_notif_slot_flush_submit(slot, issue_flags);
+	}
+out:
+	io_ring_submit_unlock(ctx, issue_flags);
+	if (ret < 0)
+		req_set_fail(req);
+	__io_req_complete(req, issue_flags, ret, 0);
+	return 0;
+}
+
 static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
@@ -8315,6 +8360,8 @@ static int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags)
 	switch (req->rsrc_update.type) {
 	case IORING_RSRC_UPDATE_FILES:
 		return io_files_update(req, issue_flags);
+	case IORING_RSRC_UPDATE_NOTIF:
+		return io_notif_update(req, issue_flags);
 	}
 	return -EINVAL;
 }
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 5f574558b96c..19b9d7a2da29 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -266,6 +266,7 @@ enum io_uring_op {
  */
 enum {
 	IORING_RSRC_UPDATE_FILES,
+	IORING_RSRC_UPDATE_NOTIF,
 };
 
 /*
-- 
2.36.1