io_uring: don't inline io_put_kbuf

io_put_kbuf() is huge, don't bloat the kernel with inlining.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/2e21ccf0be471ffa654032914b9430813cae53f8.1655371007.git.asml.silence@gmail.comReviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/kbuf.c

@@ -83,6 +83,39 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx,
 	return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
 }
 
+unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
+{
+	unsigned int cflags;
+
+	/*
+	 * We can add this buffer back to two lists:
+	 *
+	 * 1) The io_buffers_cache list. This one is protected by the
+	 *    ctx->uring_lock. If we already hold this lock, add back to this
+	 *    list as we can grab it from issue as well.
+	 * 2) The io_buffers_comp list. This one is protected by the
+	 *    ctx->completion_lock.
+	 *
+	 * We migrate buffers from the comp_list to the issue cache list
+	 * when we need one.
+	 */
+	if (req->flags & REQ_F_BUFFER_RING) {
+		/* no buffers to recycle for this case */
+		cflags = __io_put_kbuf_list(req, NULL);
+	} else if (issue_flags & IO_URING_F_UNLOCKED) {
+		struct io_ring_ctx *ctx = req->ctx;
+
+		spin_lock(&ctx->completion_lock);
+		cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp);
+		spin_unlock(&ctx->completion_lock);
+	} else {
+		lockdep_assert_held(&req->ctx->uring_lock);
+
+		cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
+	}
+	return cflags;
+}
+
 static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
 					      struct io_buffer_list *bl)
 {

io_uring/kbuf.h

@@ -47,6 +47,8 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
 int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 
+unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
+
 static inline bool io_do_buffer_select(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_BUFFER_SELECT))
@@ -79,7 +81,8 @@ static inline void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	__io_kbuf_recycle(req, issue_flags);
 }
 
-static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list)
+static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req,
+					      struct list_head *list)
 {
 	if (req->flags & REQ_F_BUFFER_RING) {
 		if (req->buf_list)
@@ -99,44 +102,15 @@ static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
 
 	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
 		return 0;
-	return __io_put_kbuf(req, &req->ctx->io_buffers_comp);
+	return __io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
 }
 
 static inline unsigned int io_put_kbuf(struct io_kiocb *req,
 				       unsigned issue_flags)
 {
-	unsigned int cflags;
 
 	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
 		return 0;
-
-	/*
-	 * We can add this buffer back to two lists:
-	 *
-	 * 1) The io_buffers_cache list. This one is protected by the
-	 *    ctx->uring_lock. If we already hold this lock, add back to this
-	 *    list as we can grab it from issue as well.
-	 * 2) The io_buffers_comp list. This one is protected by the
-	 *    ctx->completion_lock.
-	 *
-	 * We migrate buffers from the comp_list to the issue cache list
-	 * when we need one.
-	 */
-	if (req->flags & REQ_F_BUFFER_RING) {
-		/* no buffers to recycle for this case */
-		cflags = __io_put_kbuf(req, NULL);
-	} else if (issue_flags & IO_URING_F_UNLOCKED) {
-		struct io_ring_ctx *ctx = req->ctx;
-
-		spin_lock(&ctx->completion_lock);
-		cflags = __io_put_kbuf(req, &ctx->io_buffers_comp);
-		spin_unlock(&ctx->completion_lock);
-	} else {
-		lockdep_assert_held(&req->ctx->uring_lock);
-
-		cflags = __io_put_kbuf(req, &req->ctx->io_buffers_cache);
-	}
-
-	return cflags;
+	return __io_put_kbuf(req, issue_flags);
 }
 #endif