io_uring/kbuf: add support for incremental buffer consumption

By default, any recv/read operation that uses provided buffers will
consume at least 1 buffer fully (and maybe more, in case of bundles).
This adds support for incremental consumption, meaning that an
application may add large buffers, and each read/recv will just consume
the part of the buffer that it needs.

For example, let's say an application registers 1MB buffers in a
provided buffer ring, for streaming receives. If it gets a short recv,
then the full 1MB buffer will be consumed and passed back to the
application. With incremental consumption, only the part that was
actually used is consumed, and the buffer remains the current one.

This means that both the application and the kernel needs to keep track
of what the current receive point is. Each recv will still pass back a
buffer ID and the size consumed, the only difference is that before the
next receive would always be the next buffer in the ring. Now the same
buffer ID may return multiple receives, each at an offset into that
buffer from where the previous receive left off. Example:

Application registers a provided buffer ring, and adds two 32K buffers
to the ring.

Buffer1 address: 0x1000000 (buffer ID 0)
Buffer2 address: 0x2000000 (buffer ID 1)

A recv completion is received with the following values:

cqe->res	0x1000	(4k bytes received)
cqe->flags	0x11	(CQE_F_BUFFER|CQE_F_BUF_MORE set, buffer ID 0)

and the application now knows that 4096b of data is available at
0x1000000, the start of that buffer, and that more data from this buffer
will be coming. Now the next receive comes in:

cqe->res	0x2010	(8k bytes received)
cqe->flags	0x11	(CQE_F_BUFFER|CQE_F_BUF_MORE set, buffer ID 0)

which tells the application that 8k is available where the last
completion left off, at 0x1001000. Next completion is:

cqe->res	0x5000	(20k bytes received)
cqe->flags	0x1	(CQE_F_BUFFER set, buffer ID 0)

and the application now knows that 20k of data is available at
0x1003000, which is where the previous receive ended. CQE_F_BUF_MORE
isn't set, as no more data is available in this buffer ID. The next
completion is then:

cqe->res	0x1000	(4k bytes received)
cqe->flags	0x10001	(CQE_F_BUFFER|CQE_F_BUF_MORE set, buffer ID 1)

which tells the application that buffer ID 1 is now the current one,
hence there's 4k of valid data at 0x2000000. 0x2001000 will be the next
receive point for this buffer ID.

When a buffer will be reused by future CQE completions,
IORING_CQE_BUF_MORE will be set in cqe->flags. This tells the application
that the kernel isn't done with the buffer yet, and that it should expect
more completions for this buffer ID. Will only be set by provided buffer
rings setup with IOU_PBUF_RING INC, as that's the only type of buffer
that will see multiple consecutive completions for the same buffer ID.
For any other provided buffer type, any completion that passes back
a buffer to the application is final.

Once a buffer has been fully consumed, the buffer ring head is
incremented and the next receive will indicate the next buffer ID in the
CQE cflags.

On the send side, the application can manage how much data is sent from
an existing buffer by setting sqe->len to the desired send length.

An application can request incremental consumption by setting
IOU_PBUF_RING_INC in the provided buffer ring registration. Outside of
that, any provided buffer ring setup and buffer additions is done like
before, no changes there. The only change is in how an application may
see multiple completions for the same buffer ID, hence needing to know
where the next receive will happen.

Note that like existing provided buffer rings, this should not be used
with IOSQE_ASYNC, as both really require the ring to remain locked over
the duration of the buffer selection and the operation completion. It
will consume a buffer otherwise regardless of the size of the IO done.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 64 insertions, 20 deletions

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 55d01861d8c5..1f503bcc9c9f 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -212,14 +212,25 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 	buf = io_ring_head_to_buf(br, head, bl->mask);
 	if (arg->max_len) {
 		u32 len = READ_ONCE(buf->len);
-		size_t needed;
 
 		if (unlikely(!len))
 			return -ENOBUFS;
-		needed = (arg->max_len + len - 1) / len;
-		needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
-		if (nr_avail > needed)
-			nr_avail = needed;
+		/*
+		 * Limit incremental buffers to 1 segment. No point trying
+		 * to peek ahead and map more than we need, when the buffers
+		 * themselves should be large when setup with
+		 * IOU_PBUF_RING_INC.
+		 */
+		if (bl->flags & IOBL_INC) {
+			nr_avail = 1;
+		} else {
+			size_t needed;
+
+			needed = (arg->max_len + len - 1) / len;
+			needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
+			if (nr_avail > needed)
+				nr_avail = needed;
+		}
 	}
 
 	/*
@@ -244,16 +255,21 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 
 	req->buf_index = buf->bid;
 	do {
-		/* truncate end piece, if needed */
-		if (buf->len > arg->max_len)
-			buf->len = arg->max_len;
+		u32 len = buf->len;
+
+		/* truncate end piece, if needed, for non partial buffers */
+		if (len > arg->max_len) {
+			len = arg->max_len;
+			if (!(bl->flags & IOBL_INC))
+				buf->len = len;
+		}
 
 		iov->iov_base = u64_to_user_ptr(buf->addr);
-		iov->iov_len = buf->len;
+		iov->iov_len = len;
 		iov++;
 
-		arg->out_len += buf->len;
-		arg->max_len -= buf->len;
+		arg->out_len += len;
+		arg->max_len -= len;
 		if (!arg->max_len)
 			break;
 
@@ -675,7 +691,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 
 	if (reg.resv[0] || reg.resv[1] || reg.resv[2])
 		return -EINVAL;
-	if (reg.flags & ~IOU_PBUF_RING_MMAP)
+	if (reg.flags & ~(IOU_PBUF_RING_MMAP | IOU_PBUF_RING_INC))
 		return -EINVAL;
 	if (!(reg.flags & IOU_PBUF_RING_MMAP)) {
 		if (!reg.ring_addr)
@@ -713,6 +729,8 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (!ret) {
 		bl->nr_entries = reg.ring_entries;
 		bl->mask = reg.ring_entries - 1;
+		if (reg.flags & IOU_PBUF_RING_INC)
+			bl->flags |= IOBL_INC;
 
 		io_buffer_add_list(ctx, bl, reg.bgid);
 		return 0;
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index b41e2a0a0505..36aadfe5ac00 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -9,6 +9,9 @@ enum {
 	IOBL_BUF_RING	= 1,
 	/* ring mapped provided buffers, but mmap'ed by application */
 	IOBL_MMAP	= 2,
+	/* buffers are consumed incrementally rather than always fully */
+	IOBL_INC	= 4,
+
 };
 
 struct io_buffer_list {
@@ -124,24 +127,45 @@ static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 /* Mapped buffer ring, return io_uring_buf from head */
 #define io_ring_head_to_buf(br, head, mask)	&(br)->bufs[(head) & (mask)]
 
-static inline void io_kbuf_commit(struct io_kiocb *req,
+static inline bool io_kbuf_commit(struct io_kiocb *req,
 				  struct io_buffer_list *bl, int len, int nr)
 {
 	if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT)))
-		return;
-	bl->head += nr;
+		return true;
+
 	req->flags &= ~REQ_F_BUFFERS_COMMIT;
+
+	if (unlikely(len < 0))
+		return true;
+
+	if (bl->flags & IOBL_INC) {
+		struct io_uring_buf *buf;
+
+		buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
+		if (WARN_ON_ONCE(len > buf->len))
+			len = buf->len;
+		buf->len -= len;
+		if (buf->len) {
+			buf->addr += len;
+			return false;
+		}
+	}
+
+	bl->head += nr;
+	return true;
 }
 
-static inline void __io_put_kbuf_ring(struct io_kiocb *req, int len, int nr)
+static inline bool __io_put_kbuf_ring(struct io_kiocb *req, int len, int nr)
 {
 	struct io_buffer_list *bl = req->buf_list;
+	bool ret = true;
 
 	if (bl) {
-		io_kbuf_commit(req, bl, len, nr);
+		ret = io_kbuf_commit(req, bl, len, nr);
 		req->buf_index = bl->bgid;
 	}
 	req->flags &= ~REQ_F_BUFFER_RING;
+	return ret;
 }
 
 static inline void __io_put_kbuf_list(struct io_kiocb *req, int len,
@@ -176,10 +200,12 @@ static inline unsigned int __io_put_kbufs(struct io_kiocb *req, int len,
 		return 0;
 
 	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
-	if (req->flags & REQ_F_BUFFER_RING)
-		__io_put_kbuf_ring(req, len, nbufs);
-	else
+	if (req->flags & REQ_F_BUFFER_RING) {
+		if (!__io_put_kbuf_ring(req, len, nbufs))
+			ret |= IORING_CQE_F_BUF_MORE;
+	} else {
 		__io_put_kbuf(req, len, issue_flags);
+	}
 	return ret;
 }