io_uring/cmd: add iovec cache for commands

Add iou_vec to commands and wire caching for it, but don't expose it to
users just yet. We need the vec cleared on initial alloc, but since
we can't place it at the beginning at the moment, zero the entire
async_data. It's cached, and the performance effects only the initial
allocation, and it might be not a bad idea since we're exposing those
bits to outside drivers.

Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/c0f2145b75791bc6106eb4e72add2cf6a2c72a7a.1742579999.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>

Author: isilence

io_uring/io_uring.c

@@ -289,7 +289,7 @@ static void io_free_alloc_caches(struct io_ring_ctx *ctx)
 	io_alloc_cache_free(&ctx->apoll_cache, kfree);
 	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->cmd_cache, kfree);
+	io_alloc_cache_free(&ctx->cmd_cache, io_cmd_cache_free);
 	io_alloc_cache_free(&ctx->msg_cache, kfree);
 	io_futex_cache_free(ctx);
 	io_rsrc_cache_free(ctx);
@@ -335,7 +335,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 			    sizeof(struct io_async_rw),
 			    offsetof(struct io_async_rw, clear));
 	ret |= io_alloc_cache_init(&ctx->cmd_cache, IO_ALLOC_CACHE_MAX,
-			    sizeof(struct io_async_cmd), 0);
+			    sizeof(struct io_async_cmd),
+			    sizeof(struct io_async_cmd));
 	spin_lock_init(&ctx->msg_lock);
 	ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX,
 			    sizeof(struct io_kiocb), 0);

io_uring/opdef.c

@@ -755,6 +755,7 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_URING_CMD] = {
 		.name			= "URING_CMD",
+		.cleanup		= io_uring_cmd_cleanup,
 	},
 	[IORING_OP_SEND_ZC] = {
 		.name			= "SEND_ZC",

io_uring/uring_cmd.c

@@ -16,6 +16,14 @@
 #include "rsrc.h"
 #include "uring_cmd.h"
 
+void io_cmd_cache_free(const void *entry)
+{
+	struct io_async_cmd *ac = (struct io_async_cmd *)entry;
+
+	io_vec_free(&ac->vec);
+	kfree(ac);
+}
+
 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);
@@ -29,13 +37,23 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		return;
+
+	io_alloc_cache_vec_kasan(&ac->vec);
+	if (ac->vec.nr > IO_VEC_CACHE_SOFT_CAP)
+		io_vec_free(&ac->vec);
+
 	if (io_alloc_cache_put(&req->ctx->cmd_cache, cache)) {
 		ioucmd->sqe = NULL;
 		req->async_data = NULL;
-		req->flags &= ~REQ_F_ASYNC_DATA;
+		req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
 	}
 }
 
+void io_uring_cmd_cleanup(struct io_kiocb *req)
+{
+	io_req_uring_cleanup(req, 0);
+}
+
 bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
 				   struct io_uring_task *tctx, bool cancel_all)
 {

io_uring/uring_cmd.h

@@ -1,13 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/io_uring/cmd.h>
+#include <linux/io_uring_types.h>
 
 struct io_async_cmd {
 	struct io_uring_cmd_data	data;
+	struct iou_vec			vec;
 };
 
 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);
+void io_uring_cmd_cleanup(struct io_kiocb *req);
 
 bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
 				   struct io_uring_task *tctx, bool cancel_all);
+
+void io_cmd_cache_free(const void *entry);