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;
 }