diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 60d7e35fc303685b85cf834f027f3d37e5b96bbb..0f24fdad19c2a85b7958b6a861f7dea56e7fb8ad 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -301,6 +301,7 @@ struct io_ring_ctx {
 		struct io_alloc_cache	apoll_cache;
 		struct io_alloc_cache	netmsg_cache;
 		struct io_alloc_cache	rw_cache;
+		struct io_alloc_cache	uring_cache;
 
 		/*
 		 * Any cancelable uring_cmd is added to this list in
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index b0554d1229311a1b843519d0a8ca2864eca6d3da..a868c0a253a6b1401462e95131b890524be186dd 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -313,6 +313,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 			    sizeof(struct io_async_msghdr));
 	io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX,
 			    sizeof(struct io_async_rw));
+	io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX,
+			    sizeof(struct uring_cache));
 	io_futex_cache_init(ctx);
 	init_completion(&ctx->ref_comp);
 	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
@@ -2826,6 +2828,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free);
 	io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
 	io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
+	io_alloc_cache_free(&ctx->uring_cache, io_uring_cache_free);
 	io_futex_cache_free(ctx);
 	io_destroy_buffers(ctx);
 	mutex_unlock(&ctx->uring_lock);
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 1951107210d495e5e13672590d77caee27b637bf..745246086c233ee3dfd78b1452e7b6dde86319c1 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -677,7 +677,6 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_URING_CMD] = {
 		.name			= "URING_CMD",
 		.async_size		= 2 * sizeof(struct io_uring_sqe),
-		.prep_async		= io_uring_cmd_prep_async,
 	},
 	[IORING_OP_SEND_ZC] = {
 		.name			= "SEND_ZC",
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 4614ce734fee0684828edc03d7484d3a33ff0556..9bd0ba87553ff059a9273527eed356f5f1ce072f 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -14,6 +14,38 @@
 #include "rsrc.h"
 #include "uring_cmd.h"
 
+static struct uring_cache *io_uring_async_get(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_cache_entry *entry;
+	struct uring_cache *cache;
+
+	entry = io_alloc_cache_get(&ctx->uring_cache);
+	if (entry) {
+		cache = container_of(entry, struct uring_cache, cache);
+		req->flags |= REQ_F_ASYNC_DATA;
+		req->async_data = cache;
+		return cache;
+	}
+	if (!io_alloc_async_data(req))
+		return req->async_data;
+	return NULL;
+}
+
+static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
+	struct uring_cache *cache = req->async_data;
+
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		return;
+	if (io_alloc_cache_put(&req->ctx->uring_cache, &cache->cache)) {
+		ioucmd->sqe = NULL;
+		req->async_data = NULL;
+		req->flags &= ~REQ_F_ASYNC_DATA;
+	}
+}
+
 bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
 				   struct task_struct *task, bool cancel_all)
 {
@@ -128,6 +160,7 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
 	io_req_set_res(req, ret, 0);
 	if (req->ctx->flags & IORING_SETUP_CQE32)
 		io_req_set_cqe32_extra(req, res2, 0);
+	io_req_uring_cleanup(req, issue_flags);
 	if (req->ctx->flags & IORING_SETUP_IOPOLL) {
 		/* order with io_iopoll_req_issued() checking ->iopoll_complete */
 		smp_store_release(&req->iopoll_completed, 1);
@@ -142,13 +175,19 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_done);
 
-int io_uring_cmd_prep_async(struct io_kiocb *req)
+static int io_uring_cmd_prep_setup(struct io_kiocb *req,
+				   const struct io_uring_sqe *sqe)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
+	struct uring_cache *cache;
 
-	memcpy(req->async_data, ioucmd->sqe, uring_sqe_size(req->ctx));
-	ioucmd->sqe = req->async_data;
-	return 0;
+	cache = io_uring_async_get(req);
+	if (cache) {
+		memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx));
+		ioucmd->sqe = req->async_data;
+		return 0;
+	}
+	return -ENOMEM;
 }
 
 int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -173,9 +212,9 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		req->imu = ctx->user_bufs[index];
 		io_req_set_rsrc_node(req, ctx, 0);
 	}
-	ioucmd->sqe = sqe;
 	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
-	return 0;
+
+	return io_uring_cmd_prep_setup(req, sqe);
 }
 
 int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
@@ -206,23 +245,14 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
-	if (ret == -EAGAIN) {
-		if (!req_has_async_data(req)) {
-			if (io_alloc_async_data(req))
-				return -ENOMEM;
-			io_uring_cmd_prep_async(req);
-		}
-		return -EAGAIN;
-	}
-
-	if (ret != -EIOCBQUEUED) {
-		if (ret < 0)
-			req_set_fail(req);
-		io_req_set_res(req, ret, 0);
+	if (ret == -EAGAIN || ret == -EIOCBQUEUED)
 		return ret;
-	}
 
-	return IOU_ISSUE_SKIP_COMPLETE;
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_uring_cleanup(req, issue_flags);
+	io_req_set_res(req, ret, 0);
+	return ret;
 }
 
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
@@ -311,3 +341,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_sock);
 #endif
+
+void io_uring_cache_free(struct io_cache_entry *entry)
+{
+	kfree(container_of(entry, struct uring_cache, cache));
+}
diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h
index 7356bf9aa65580f6551669de78861977f58bdf1c..b0ccff7091eec3eb1f9db16fc36e71caec2e49ac 100644
--- a/io_uring/uring_cmd.h
+++ b/io_uring/uring_cmd.h
@@ -1,8 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
 
+struct uring_cache {
+	union {
+		struct io_cache_entry cache;
+		struct io_uring_sqe sqes[2];
+	};
+};
+
 int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags);
 int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_uring_cmd_prep_async(struct io_kiocb *req);
+void io_uring_cache_free(struct io_cache_entry *entry);
 
 bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
-				   struct task_struct *task, bool cancel_all);
\ No newline at end of file
+				   struct task_struct *task, bool cancel_all);