[PATCH V10 08/12] io_uring: reuse io_mapped_buf for kernel buffer

[Ming Lei <ming.lei@redhat.com>]

Prepare for supporting kernel buffer in case of io group, in which group
leader leases kernel buffer to io_uring, and consumed by io_uring OPs.

So reuse io_mapped_buf for group kernel buffer, and unfortunately
io_import_fixed() can't be reused since userspace fixed buffer is
virt-contiguous, but it isn't true for kernel buffer.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 include/linux/io_uring_types.h | 19 +++++++++++++++++++
 io_uring/kbuf.c                | 34 ++++++++++++++++++++++++++++++++++
 io_uring/kbuf.h                |  3 +++
 io_uring/rsrc.c                |  1 +
 io_uring/rsrc.h                | 10 ----------
 5 files changed, 57 insertions(+), 10 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index d060ce5e6145..03abaeef4a67 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -2,6 +2,7 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/bvec.h>
 #include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
@@ -39,6 +40,24 @@ enum io_uring_cmd_flags {
 	IO_URING_F_COMPAT		= (1 << 12),
 };
 
+struct io_mapped_buf {
+	u64		addr;
+	unsigned int	len;
+	unsigned int	nr_bvecs;
+	refcount_t	refs;
+	union {
+		/* for userspace buffer only */
+		unsigned int	acct_pages;
+		/* offset in the 1st bvec, for kbuf only */
+		unsigned int	offset;
+	};
+	const struct bio_vec	*pbvec; /* pbvec is only for kbuf */
+	unsigned int	folio_shift:6;
+	unsigned int	dir:1;		/* ITER_DEST or ITER_SOURCE */
+	unsigned int	kbuf:1;		/* kernel buffer or not */
+	struct bio_vec	bvec[] __counted_by(nr_bvecs);
+};
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index d407576ddfb7..c4a776860cb4 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -838,3 +838,37 @@ int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma)
 	io_put_bl(ctx, bl);
 	return ret;
 }
+
+/*
+ * kernel buffer is built over generic bvec, and can't be always
+ * virt-contiguous, which is different with userspace fixed buffer,
+ * so we can't reuse io_import_fixed() here
+ *
+ * Also kernel buffer lifetime is bound with request, and we needn't
+ * to use rsrc_node to track its lifetime
+ */
+int io_import_kbuf(int ddir, struct iov_iter *iter,
+		    const struct io_mapped_buf *kbuf,
+		    u64 buf_off, size_t len)
+{
+	unsigned long offset = kbuf->offset;
+
+	WARN_ON_ONCE(!kbuf->kbuf);
+
+	if (ddir != kbuf->dir)
+		return -EINVAL;
+
+	if (unlikely(buf_off > kbuf->len))
+		return -EFAULT;
+
+	if (unlikely(len > kbuf->len - buf_off))
+		return -EFAULT;
+
+	offset += buf_off;
+	iov_iter_bvec(iter, ddir, kbuf->pbvec, kbuf->nr_bvecs, offset + len);
+
+	if (offset)
+		iov_iter_advance(iter, offset);
+
+	return 0;
+}
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 36aadfe5ac00..04ccd52dd0ad 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -88,6 +88,9 @@ void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl);
 struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
 				      unsigned long bgid);
 int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma);
+int io_import_kbuf(int ddir, struct iov_iter *iter,
+		    const struct io_mapped_buf *kbuf,
+		    u64 buf_off, size_t len);
 
 static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
 {
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 99ff2797e6ec..b0b60ae0456a 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -771,6 +771,7 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
 	imu->len = iov->iov_len;
 	imu->nr_bvecs = nr_pages;
 	imu->folio_shift = PAGE_SHIFT;
+	imu->kbuf = 0;
 	if (coalesced)
 		imu->folio_shift = data.folio_shift;
 	refcount_set(&imu->refs, 1);
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index bf0824b4beb6..3bc3a484fbba 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -28,16 +28,6 @@ struct io_rsrc_node {
 	};
 };
 
-struct io_mapped_buf {
-	u64		addr;
-	unsigned int	len;
-	unsigned int	nr_bvecs;
-	refcount_t	refs;
-	unsigned int	acct_pages;
-	unsigned int	folio_shift:6;
-	struct bio_vec	bvec[] __counted_by(nr_bvecs);
-};
-
 struct io_imu_folio_data {
 	/* Head folio can be partially included in the fixed buf */
 	unsigned int	nr_pages_head;
-- 
2.47.0