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 18/29] io_uring: add notification slot registration
Date:   Tue, 28 Jun 2022 19:56:40 +0100
Message-Id: <af374ecb2ec795a5fdd35cd2e11540f99d465860.1653992701.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

Let the userspace to register and unregister notification slots.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c                 | 54 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/io_uring.h | 16 +++++++++++
 2 files changed, 70 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 9ade0ea8552b..22427893549a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -94,6 +94,8 @@
 #define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
 
+#define IORING_MAX_NOTIF_SLOTS	(1U << 10)
+
 /* only define max */
 #define IORING_MAX_FIXED_FILES	(1U << 20)
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
@@ -2972,6 +2974,49 @@ static __cold int io_notif_unregister(struct io_ring_ctx *ctx)
 	kvfree(ctx->notif_slots);
 	ctx->notif_slots = NULL;
 	ctx->nr_notif_slots = 0;
+	io_notif_cache_purge(ctx);
+	return 0;
+}
+
+static __cold int io_notif_register(struct io_ring_ctx *ctx,
+				    void __user *arg, unsigned int size)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_uring_notification_slot __user *slots;
+	struct io_uring_notification_slot slot;
+	struct io_uring_notification_register reg;
+	unsigned i;
+
+	if (ctx->nr_notif_slots)
+		return -EBUSY;
+	if (size != sizeof(reg))
+		return -EINVAL;
+	if (copy_from_user(&reg, arg, sizeof(reg)))
+		return -EFAULT;
+	if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS)
+		return -EINVAL;
+	if (reg.resv || reg.resv2 || reg.resv3)
+		return -EINVAL;
+
+	slots = u64_to_user_ptr(reg.data);
+	ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]),
+				GFP_KERNEL_ACCOUNT);
+	if (!ctx->notif_slots)
+		return -ENOMEM;
+
+	for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) {
+		struct io_notif_slot *notif_slot = &ctx->notif_slots[i];
+
+		if (copy_from_user(&slot, &slots[i], sizeof(slot))) {
+			io_notif_unregister(ctx);
+			return -EFAULT;
+		}
+		if (slot.resv[0] | slot.resv[1] | slot.resv[2]) {
+			io_notif_unregister(ctx);
+			return -EINVAL;
+		}
+		notif_slot->tag = slot.tag;
+	}
 	return 0;
 }
 
@@ -13378,6 +13423,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_unregister_pbuf_ring(ctx, arg);
 		break;
+	case IORING_REGISTER_NOTIFIERS:
+		ret = io_notif_register(ctx, arg, nr_args);
+		break;
+	case IORING_UNREGISTER_NOTIFIERS:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_notif_unregister(ctx);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 53e7dae92e42..96193bbda2e4 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -417,6 +417,9 @@ enum {
 	IORING_REGISTER_PBUF_RING		= 22,
 	IORING_UNREGISTER_PBUF_RING		= 23,
 
+	IORING_REGISTER_NOTIFIERS		= 24,
+	IORING_UNREGISTER_NOTIFIERS		= 25,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -463,6 +466,19 @@ struct io_uring_rsrc_update2 {
 	__u32 resv2;
 };
 
+struct io_uring_notification_slot {
+	__u64 tag;
+	__u64 resv[3];
+};
+
+struct io_uring_notification_register {
+	__u32 nr_slots;
+	__u32 resv;
+	__u64 resv2;
+	__u64 data;
+	__u64 resv3;
+};
+
 /* Skip updating fd indexes set to this value in the fd table */
 #define IORING_REGISTER_FILES_SKIP	(-2)
 
-- 
2.36.1