[PATCHv8 4/6] io_uring: add support for kernel registered bvecs

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

Provide an interface for the kernel to leverage the existing
pre-registered buffers that io_uring provides. User space can reference
these later to achieve zero-copy IO.

User space must register an empty fixed buffer table with io_uring in
order for the kernel to make use of it.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/io_uring/cmd.h |   7 ++
 io_uring/io_uring.c          |   3 +
 io_uring/rsrc.c              | 123 +++++++++++++++++++++++++++++++++--
 io_uring/rsrc.h              |   9 +++
 io_uring/rw.c                |   3 +
 5 files changed, 138 insertions(+), 7 deletions(-)

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 87150dc0a07cf..cf8d80d847344 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -4,6 +4,7 @@
 
 #include <uapi/linux/io_uring.h>
 #include <linux/io_uring_types.h>
+#include <linux/blk-mq.h>
 
 /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
 #define IORING_URING_CMD_CANCELABLE	(1U << 30)
@@ -125,4 +126,10 @@ static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_ur
 	return cmd_to_io_kiocb(cmd)->async_data;
 }
 
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
+			    void (*release)(void *), unsigned int index,
+			    unsigned int issue_flags);
+void io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
+			       unsigned int issue_flags);
+
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index db1c0792def63..2f5dd47e7dbf5 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3947,6 +3947,9 @@ static int __init io_uring_init(void)
 
 	io_uring_optable_init();
 
+	/* imu->dir is u8 */
+	BUILD_BUG_ON((IO_IMU_DEST | IO_IMU_SOURCE) > U8_MAX);
+
 	/*
 	 * Allow user copy in the per-command field, which starts after the
 	 * file in io_kiocb and until the opcode field. The openat2 handling
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index f814526982c36..0eceaf2e03777 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -9,6 +9,7 @@
 #include <linux/hugetlb.h>
 #include <linux/compat.h>
 #include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -101,17 +102,23 @@ int io_buffer_validate(struct iovec *iov)
 	return 0;
 }
 
-static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
+static void io_release_ubuf(void *priv)
 {
-	struct io_mapped_ubuf *imu = node->buf;
+	struct io_mapped_ubuf *imu = priv;
 	unsigned int i;
 
-	if (!refcount_dec_and_test(&imu->refs))
-		return;
 	for (i = 0; i < imu->nr_bvecs; i++)
 		unpin_user_page(imu->bvec[i].bv_page);
+}
+
+static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf *imu)
+{
+	if (!refcount_dec_and_test(&imu->refs))
+		return;
+
 	if (imu->acct_pages)
 		io_unaccount_mem(ctx, imu->acct_pages);
+	imu->release(imu->priv);
 	kvfree(imu);
 }
 
@@ -451,7 +458,7 @@ void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
 		break;
 	case IORING_RSRC_BUFFER:
 		if (node->buf)
-			io_buffer_unmap(ctx, node);
+			io_buffer_unmap(ctx, node->buf);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -761,6 +768,10 @@ 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->release = io_release_ubuf;
+	imu->priv = imu;
+	imu->is_kbuf = false;
+	imu->dir = IO_IMU_DEST | IO_IMU_SOURCE;
 	if (coalesced)
 		imu->folio_shift = data.folio_shift;
 	refcount_set(&imu->refs, 1);
@@ -857,6 +868,95 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 	return ret;
 }
 
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
+			    void (*release)(void *), 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 req_iterator rq_iter;
+	struct io_mapped_ubuf *imu;
+	struct io_rsrc_node *node;
+	struct bio_vec bv, *bvec;
+	u16 nr_bvecs;
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	if (index >= data->nr) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+	index = array_index_nospec(index, data->nr);
+
+	if (data->nodes[index]) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	node = io_rsrc_node_alloc(IORING_RSRC_BUFFER);
+	if (!node) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	nr_bvecs = blk_rq_nr_phys_segments(rq);
+	imu = kvmalloc(struct_size(imu, bvec, nr_bvecs), GFP_KERNEL);
+	if (!imu) {
+		kfree(node);
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	imu->ubuf = 0;
+	imu->len = blk_rq_bytes(rq);
+	imu->acct_pages = 0;
+	imu->folio_shift = PAGE_SHIFT;
+	imu->nr_bvecs = nr_bvecs;
+	refcount_set(&imu->refs, 1);
+	imu->release = release;
+	imu->priv = rq;
+	imu->is_kbuf = true;
+
+	if (op_is_write(req_op(rq)))
+		imu->dir = IO_IMU_SOURCE;
+	else
+		imu->dir = IO_IMU_DEST;
+
+	bvec = imu->bvec;
+	rq_for_each_bvec(bv, rq, rq_iter)
+		*bvec++ = bv;
+
+	node->buf = imu;
+	data->nodes[index] = node;
+unlock:
+	io_ring_submit_unlock(ctx, issue_flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(io_buffer_register_bvec);
+
+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_node *node;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	if (index >= data->nr)
+		goto unlock;
+	index = array_index_nospec(index, data->nr);
+
+	node = data->nodes[index];
+	if (!node || !node->buf->is_kbuf)
+		goto unlock;
+
+	io_put_rsrc_node(ctx, node);
+	data->nodes[index] = NULL;
+unlock:
+	io_ring_submit_unlock(ctx, issue_flags);
+}
+EXPORT_SYMBOL_GPL(io_buffer_unregister_bvec);
+
 static int io_import_fixed(int ddir, struct iov_iter *iter,
 			   struct io_mapped_ubuf *imu,
 			   u64 buf_addr, size_t len)
@@ -871,6 +971,8 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 	/* not inside the mapped region */
 	if (unlikely(buf_addr < imu->ubuf || buf_end > (imu->ubuf + imu->len)))
 		return -EFAULT;
+	if (!(imu->dir & (1 << ddir)))
+		return -EFAULT;
 
 	/*
 	 * Might not be a start of buffer, set size appropriately
@@ -883,8 +985,8 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 		/*
 		 * Don't use iov_iter_advance() here, as it's really slow for
 		 * using the latter parts of a big fixed buffer - it iterates
-		 * over each segment manually. We can cheat a bit here, because
-		 * we know that:
+		 * over each segment manually. We can cheat a bit here for user
+		 * registered nodes, because we know that:
 		 *
 		 * 1) it's a BVEC iter, we set it up
 		 * 2) all bvecs are the same in size, except potentially the
@@ -898,8 +1000,15 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 		 */
 		const struct bio_vec *bvec = imu->bvec;
 
+		/*
+		 * Kernel buffer bvecs, on the other hand, don't necessarily
+		 * have the size property of user registered ones, so we have
+		 * to use the slow iter advance.
+		 */
 		if (offset < bvec->bv_len) {
 			iter->iov_offset = offset;
+		} else if (imu->is_kbuf) {
+			iov_iter_advance(iter, offset);
 		} else {
 			unsigned long seg_skip;
 
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index f0e9080599646..7600e2736eeb3 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -20,6 +20,11 @@ struct io_rsrc_node {
 	};
 };
 
+enum {
+	IO_IMU_DEST	= 1 << ITER_DEST,
+	IO_IMU_SOURCE	= 1 << ITER_SOURCE,
+};
+
 struct io_mapped_ubuf {
 	u64		ubuf;
 	unsigned int	len;
@@ -27,6 +32,10 @@ struct io_mapped_ubuf {
 	unsigned int    folio_shift;
 	refcount_t	refs;
 	unsigned long	acct_pages;
+	void		(*release)(void *);
+	void		*priv;
+	bool		is_kbuf;
+	u8		dir;
 	struct bio_vec	bvec[] __counted_by(nr_bvecs);
 };
 
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 7bc23802a388e..5ee9f8949e8ba 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -629,6 +629,7 @@ static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
  */
 static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
 {
+	struct io_kiocb *req = cmd_to_io_kiocb(rw);
 	struct kiocb *kiocb = &rw->kiocb;
 	struct file *file = kiocb->ki_filp;
 	ssize_t ret = 0;
@@ -644,6 +645,8 @@ static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
 	if ((kiocb->ki_flags & IOCB_NOWAIT) &&
 	    !(kiocb->ki_filp->f_flags & O_NONBLOCK))
 		return -EAGAIN;
+	if ((req->flags & REQ_F_BUF_NODE) && req->buf_node->buf->is_kbuf)
+		return -EFAULT;
 
 	ppos = io_kiocb_ppos(kiocb);
 
-- 
2.43.5