From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 12 Jul 2022 20:52:42 +0000 (+0100)
Subject: io_uring: add notification slot registration
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=bc24d6bd32df0be19df3d30e74be4ba56493c0e2;p=linux.git

io_uring: add notification slot registration

Let the userspace to register and unregister notification slots.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a0aa8161fe3ebb2a4cc6e5dbd0cffb96e6881cf5.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 4c9b11e2e9915..dcfc7a0bda0ca 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -457,6 +457,10 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* zerocopy notification API */
+	IORING_REGISTER_NOTIFIERS		= 26,
+	IORING_UNREGISTER_NOTIFIERS		= 27,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -503,6 +507,19 @@ 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)
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 20e65d45ca1cd..cae11374456e9 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3870,6 +3870,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_file_alloc_range(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/io_uring/notif.c b/io_uring/notif.c
index 0a2e98bd74f69..e6d98dc208c77 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -162,5 +162,48 @@ __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;
+}
+
+__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;
 }
diff --git a/io_uring/notif.h b/io_uring/notif.h
index 1dd48efb77446..00efe164bdc4b 100644
--- a/io_uring/notif.h
+++ b/io_uring/notif.h
@@ -6,6 +6,7 @@
 #include <linux/nospec.h>
 
 #define IO_NOTIF_SPLICE_BATCH	32
+#define IORING_MAX_NOTIF_SLOTS (1U << 10)
 
 struct io_notif {
 	struct ubuf_info	uarg;
@@ -48,6 +49,8 @@ struct io_notif_slot {
 	u32			seq;
 };
 
+int io_notif_register(struct io_ring_ctx *ctx,
+		      void __user *arg, unsigned int size);
 int io_notif_unregister(struct io_ring_ctx *ctx);
 void io_notif_cache_purge(struct io_ring_ctx *ctx);