[PATCHv5 10/11] io_uring: add abstraction for buf_table rsrc data

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

We'll need to add more fields specific to the registered buffers, so
make a layer for it now. No functional change in this patch.

Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/io_uring_types.h |  6 +++-
 io_uring/fdinfo.c              |  8 +++---
 io_uring/nop.c                 |  2 +-
 io_uring/register.c            |  2 +-
 io_uring/rsrc.c                | 51 +++++++++++++++++-----------------
 5 files changed, 36 insertions(+), 33 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index c0fe8a00fe53a..a05ae4cb98a4c 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -69,6 +69,10 @@ struct io_file_table {
 	unsigned int alloc_hint;
 };
 
+struct io_buf_table {
+	struct io_rsrc_data	data;
+};
+
 struct io_hash_bucket {
 	struct hlist_head	list;
 } ____cacheline_aligned_in_smp;
@@ -293,7 +297,7 @@ struct io_ring_ctx {
 		struct io_wq_work_list	iopoll_list;
 
 		struct io_file_table	file_table;
-		struct io_rsrc_data	buf_table;
+		struct io_buf_table	buf_table;
 
 		struct io_submit_state	submit_state;
 
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f60d0a9d505e2..d389c06cbce10 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -217,12 +217,12 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 			seq_puts(m, "\n");
 		}
 	}
-	seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
-	for (i = 0; has_lock && i < ctx->buf_table.nr; i++) {
+	seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.data.nr);
+	for (i = 0; has_lock && i < ctx->buf_table.data.nr; i++) {
 		struct io_mapped_ubuf *buf = NULL;
 
-		if (ctx->buf_table.nodes[i])
-			buf = ctx->buf_table.nodes[i]->buf;
+		if (ctx->buf_table.data.nodes[i])
+			buf = ctx->buf_table.data.nodes[i]->buf;
 		if (buf)
 			seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len);
 		else
diff --git a/io_uring/nop.c b/io_uring/nop.c
index ea539531cb5f6..da8870e00eee7 100644
--- a/io_uring/nop.c
+++ b/io_uring/nop.c
@@ -66,7 +66,7 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags)
 
 		ret = -EFAULT;
 		io_ring_submit_lock(ctx, issue_flags);
-		node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
+		node = io_rsrc_node_lookup(&ctx->buf_table.data, req->buf_index);
 		if (node) {
 			io_req_assign_buf_node(req, node);
 			ret = 0;
diff --git a/io_uring/register.c b/io_uring/register.c
index cc23a4c205cd4..f15a8d52ad30f 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -926,7 +926,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	ret = __io_uring_register(ctx, opcode, arg, nr_args);
 
 	trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr,
-				ctx->buf_table.nr, ret);
+				ctx->buf_table.data.nr, ret);
 	mutex_unlock(&ctx->uring_lock);
 
 	fput(file);
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index e0c6ed3aef5b5..70558317fbb2b 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -236,9 +236,9 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
 	__u32 done;
 	int i, err;
 
-	if (!ctx->buf_table.nr)
+	if (!ctx->buf_table.data.nr)
 		return -ENXIO;
-	if (up->offset + nr_args > ctx->buf_table.nr)
+	if (up->offset + nr_args > ctx->buf_table.data.nr)
 		return -EINVAL;
 
 	for (done = 0; done < nr_args; done++) {
@@ -270,9 +270,9 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
 			}
 			node->tag = tag;
 		}
-		i = array_index_nospec(up->offset + done, ctx->buf_table.nr);
-		io_reset_rsrc_node(ctx, &ctx->buf_table, i);
-		ctx->buf_table.nodes[i] = node;
+		i = array_index_nospec(up->offset + done, ctx->buf_table.data.nr);
+		io_reset_rsrc_node(ctx, &ctx->buf_table.data, i);
+		ctx->buf_table.data.nodes[i] = node;
 		if (ctx->compat)
 			user_data += sizeof(struct compat_iovec);
 		else
@@ -550,9 +550,9 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 
 int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
 {
-	if (!ctx->buf_table.nr)
+	if (!ctx->buf_table.data.nr)
 		return -ENXIO;
-	io_rsrc_data_free(ctx, &ctx->buf_table);
+	io_rsrc_data_free(ctx, &ctx->buf_table.data);
 	return 0;
 }
 
@@ -579,8 +579,8 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
 	}
 
 	/* check previously registered pages */
-	for (i = 0; i < ctx->buf_table.nr; i++) {
-		struct io_rsrc_node *node = ctx->buf_table.nodes[i];
+	for (i = 0; i < ctx->buf_table.data.nr; i++) {
+		struct io_rsrc_node *node = ctx->buf_table.data.nodes[i];
 		struct io_mapped_ubuf *imu;
 
 		if (!node)
@@ -809,7 +809,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 
 	BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));
 
-	if (ctx->buf_table.nr)
+	if (ctx->buf_table.data.nr)
 		return -EBUSY;
 	if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS)
 		return -EINVAL;
@@ -862,7 +862,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 		data.nodes[i] = node;
 	}
 
-	ctx->buf_table = data;
+	ctx->buf_table.data = data;
 	if (ret)
 		io_sqe_buffers_unregister(ctx);
 	return ret;
@@ -873,7 +873,7 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
 			    unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
-	struct io_rsrc_data *data = &ctx->buf_table;
+	struct io_rsrc_data *data = &ctx->buf_table.data;
 	struct req_iterator rq_iter;
 	struct io_mapped_ubuf *imu;
 	struct io_rsrc_node *node;
@@ -938,7 +938,7 @@ void io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
 			       unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
-	struct io_rsrc_data *data = &ctx->buf_table;
+	struct io_rsrc_data *data = &ctx->buf_table.data;
 	struct io_rsrc_node *node;
 
 	io_ring_submit_lock(ctx, issue_flags);
@@ -1035,7 +1035,7 @@ static inline struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
 		return req->buf_node;
 
 	io_ring_submit_lock(ctx, issue_flags);
-	node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
+	node = io_rsrc_node_lookup(&ctx->buf_table.data, req->buf_index);
 	if (node)
 		io_req_assign_buf_node(req, node);
 	io_ring_submit_unlock(ctx, issue_flags);
@@ -1085,10 +1085,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	if (!arg->nr && (arg->dst_off || arg->src_off))
 		return -EINVAL;
 	/* not allowed unless REPLACE is set */
-	if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
+	if (ctx->buf_table.data.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
 		return -EBUSY;
 
-	nbufs = src_ctx->buf_table.nr;
+	nbufs = src_ctx->buf_table.data.nr;
 	if (!arg->nr)
 		arg->nr = nbufs;
 	else if (arg->nr > nbufs)
@@ -1098,13 +1098,13 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	if (check_add_overflow(arg->nr, arg->dst_off, &nbufs))
 		return -EOVERFLOW;
 
-	ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.nr));
+	ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.data.nr));
 	if (ret)
 		return ret;
 
 	/* Fill entries in data from dst that won't overlap with src */
-	for (i = 0; i < min(arg->dst_off, ctx->buf_table.nr); i++) {
-		struct io_rsrc_node *src_node = ctx->buf_table.nodes[i];
+	for (i = 0; i < min(arg->dst_off, ctx->buf_table.data.nr); i++) {
+		struct io_rsrc_node *src_node = ctx->buf_table.data.nodes[i];
 
 		if (src_node) {
 			data.nodes[i] = src_node;
@@ -1113,7 +1113,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	}
 
 	ret = -ENXIO;
-	nbufs = src_ctx->buf_table.nr;
+	nbufs = src_ctx->buf_table.data.nr;
 	if (!nbufs)
 		goto out_free;
 	ret = -EINVAL;
@@ -1133,7 +1133,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	while (nr--) {
 		struct io_rsrc_node *dst_node, *src_node;
 
-		src_node = io_rsrc_node_lookup(&src_ctx->buf_table, i);
+		src_node = io_rsrc_node_lookup(&src_ctx->buf_table.data, i);
 		if (!src_node) {
 			dst_node = NULL;
 		} else {
@@ -1155,7 +1155,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	 * old and new nodes at this point.
 	 */
 	if (arg->flags & IORING_REGISTER_DST_REPLACE)
-		io_rsrc_data_free(ctx, &ctx->buf_table);
+		io_sqe_buffers_unregister(ctx);
 
 	/*
 	 * ctx->buf_table must be empty now - either the contents are being
@@ -1163,10 +1163,9 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	 * copied to a ring that does not have buffers yet (checked at function
 	 * entry).
 	 */
-	WARN_ON_ONCE(ctx->buf_table.nr);
-	ctx->buf_table = data;
+	WARN_ON_ONCE(ctx->buf_table.data.nr);
+	ctx->buf_table.data = data;
 	return 0;
-
 out_free:
 	io_rsrc_data_free(ctx, &data);
 	return ret;
@@ -1191,7 +1190,7 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 		return -EFAULT;
 	if (buf.flags & ~(IORING_REGISTER_SRC_REGISTERED|IORING_REGISTER_DST_REPLACE))
 		return -EINVAL;
-	if (!(buf.flags & IORING_REGISTER_DST_REPLACE) && ctx->buf_table.nr)
+	if (!(buf.flags & IORING_REGISTER_DST_REPLACE) && ctx->buf_table.data.nr)
 		return -EBUSY;
 	if (memchr_inv(buf.pad, 0, sizeof(buf.pad)))
 		return -EINVAL;
-- 
2.43.5