[PATCH v4 06/25] io_uring/kbuf: add buffer ring pinning/unpinning

[Joanne Koong <joannelkoong@gmail.com>]

Add kernel APIs to pin and unpin buffer rings, preventing userspace from
unregistering a buffer ring while it is pinned by the kernel.

This provides a mechanism for kernel subsystems to safely access buffer
ring contents while ensuring the buffer ring remains valid. A pinned
buffer ring cannot be unregistered until explicitly unpinned. On the
userspace side, trying to unregister a pinned buffer will return -EBUSY.

This is a preparatory change for upcoming fuse usage of kernel-managed
buffer rings. It is necessary for fuse to pin the buffer ring because
fuse may need to select a buffer in atomic contexts, which it can only
do so by using the underlying buffer list pointer.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
---
 include/linux/io_uring/cmd.h | 17 +++++++++++++
 io_uring/kbuf.c              | 48 ++++++++++++++++++++++++++++++++++++
 io_uring/kbuf.h              |  5 ++++
 3 files changed, 70 insertions(+)

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 375fd048c4cb..702b1903e6ee 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -84,6 +84,10 @@ struct io_br_sel io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd,
 bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
 				 struct io_br_sel *sel, unsigned int issue_flags);
 
+int io_uring_buf_ring_pin(struct io_uring_cmd *cmd, unsigned buf_group,
+			  unsigned issue_flags, struct io_buffer_list **bl);
+int io_uring_buf_ring_unpin(struct io_uring_cmd *cmd, unsigned buf_group,
+			    unsigned issue_flags);
 #else
 static inline int
 io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
@@ -126,6 +130,19 @@ static inline bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
 {
 	return true;
 }
+static inline int io_uring_buf_ring_pin(struct io_uring_cmd *cmd,
+					unsigned buf_group,
+					unsigned issue_flags,
+					struct io_buffer_list **bl)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_uring_buf_ring_unpin(struct io_uring_cmd *cmd,
+					  unsigned buf_group,
+					  unsigned issue_flags)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 static inline struct io_uring_cmd *io_uring_cmd_from_tw(struct io_tw_req tw_req)
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index d9bdb2be5f13..94ab23400721 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -9,6 +9,7 @@
 #include <linux/poll.h>
 #include <linux/vmalloc.h>
 #include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -237,6 +238,51 @@ struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len,
 	return sel;
 }
 
+int io_uring_buf_ring_pin(struct io_uring_cmd *cmd, unsigned buf_group,
+			  unsigned issue_flags, struct io_buffer_list **bl)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct io_buffer_list *buffer_list;
+	int ret = -EINVAL;
+
+	io_ring_submit_lock(ctx, issue_flags);
+
+	buffer_list = io_buffer_get_list(ctx, buf_group);
+	if (buffer_list && (buffer_list->flags & IOBL_BUF_RING)) {
+		if (unlikely(buffer_list->flags & IOBL_PINNED)) {
+			ret = -EALREADY;
+		} else {
+			buffer_list->flags |= IOBL_PINNED;
+			ret = 0;
+			*bl = buffer_list;
+		}
+	}
+
+	io_ring_submit_unlock(ctx, issue_flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(io_uring_buf_ring_pin);
+
+int io_uring_buf_ring_unpin(struct io_uring_cmd *cmd, unsigned buf_group,
+		       unsigned issue_flags)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct io_buffer_list *bl;
+	int ret = -EINVAL;
+
+	io_ring_submit_lock(ctx, issue_flags);
+
+	bl = io_buffer_get_list(ctx, buf_group);
+	if (bl && (bl->flags & IOBL_BUF_RING) && (bl->flags & IOBL_PINNED)) {
+		bl->flags &= ~IOBL_PINNED;
+		ret = 0;
+	}
+
+	io_ring_submit_unlock(ctx, issue_flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(io_uring_buf_ring_unpin);
+
 /* cap it at a reasonable 256, will be one page even for 4K */
 #define PEEK_MAX_IMPORT		256
 
@@ -743,6 +789,8 @@ int io_unregister_buf_ring(struct io_ring_ctx *ctx, void __user *arg)
 		return -ENOENT;
 	if (!(bl->flags & IOBL_BUF_RING))
 		return -EINVAL;
+	if (bl->flags & IOBL_PINNED)
+		return -EBUSY;
 
 	scoped_guard(mutex, &ctx->mmap_lock)
 		xa_erase(&ctx->io_bl_xa, bl->bgid);
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 11d165888b8e..781630c2cc10 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -12,6 +12,11 @@ enum {
 	IOBL_INC		= 2,
 	/* buffers are kernel managed */
 	IOBL_KERNEL_MANAGED	= 4,
+	/*
+	 * buffer ring is pinned and cannot be unregistered by userspace until
+	 * it has been unpinned
+	 */
+	IOBL_PINNED		= 8,
 };
 
 struct io_buffer_list {
-- 
2.47.3