[PATCH v4 6/6] io_uring: add support for zone-append

[Kanchan Joshi <joshi.k@xxxxxxxxxxx>]

From: SelvaKumar S <selvakuma.s1@xxxxxxxxxxx>

Repurpose [cqe->res, cqe->flags] into cqe->res64 (signed) to report
64bit written-offset for zone-append. The appending-write which requires
reporting written-location (conveyed by IOCB_ZONE_APPEND flag) is
ensured not to be a short-write; this avoids the need to report
number-of-bytes-copied.
append-offset is returned by lower-layer to io-uring via ret2 of
ki_complete interface. Make changes to collect it and send to user-space
via cqe->res64.

Signed-off-by: SelvaKumar S <selvakuma.s1@xxxxxxxxxxx>
Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
Signed-off-by: Javier Gonzalez <javier.gonz@xxxxxxxxxxx>
---
 fs/io_uring.c                 | 49 ++++++++++++++++++++++++++++++++++++-------
 include/uapi/linux/io_uring.h |  9 ++++++--
 2 files changed, 48 insertions(+), 10 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7809ab2..6510cf5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -401,7 +401,14 @@ struct io_rw {
 	/* NOTE: kiocb has the file as the first member, so don't do it here */
 	struct kiocb			kiocb;
 	u64				addr;
-	u64				len;
+	union {
+		/*
+		 * len is used only during submission.
+		 * append_offset is used only during completion.
+		 */
+		u64			len;
+		u64			append_offset;
+	};
 };
 
 struct io_connect {
@@ -541,6 +548,7 @@ enum {
 	REQ_F_NO_FILE_TABLE_BIT,
 	REQ_F_QUEUE_TIMEOUT_BIT,
 	REQ_F_WORK_INITIALIZED_BIT,
+	REQ_F_ZONE_APPEND_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -598,6 +606,8 @@ enum {
 	REQ_F_QUEUE_TIMEOUT	= BIT(REQ_F_QUEUE_TIMEOUT_BIT),
 	/* io_wq_work is initialized */
 	REQ_F_WORK_INITIALIZED	= BIT(REQ_F_WORK_INITIALIZED_BIT),
+	/* to return zone append offset */
+	REQ_F_ZONE_APPEND = BIT(REQ_F_ZONE_APPEND_BIT),
 };
 
 struct async_poll {
@@ -1244,8 +1254,15 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 		req->flags &= ~REQ_F_OVERFLOW;
 		if (cqe) {
 			WRITE_ONCE(cqe->user_data, req->user_data);
-			WRITE_ONCE(cqe->res, req->result);
-			WRITE_ONCE(cqe->flags, req->cflags);
+			if (unlikely(req->flags & REQ_F_ZONE_APPEND)) {
+				if (likely(req->result > 0))
+					WRITE_ONCE(cqe->res64, req->rw.append_offset);
+				else
+					WRITE_ONCE(cqe->res64, req->result);
+			} else {
+				WRITE_ONCE(cqe->res, req->result);
+				WRITE_ONCE(cqe->flags, req->cflags);
+			}
 		} else {
 			WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1284,8 +1301,15 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 	cqe = io_get_cqring(ctx);
 	if (likely(cqe)) {
 		WRITE_ONCE(cqe->user_data, req->user_data);
-		WRITE_ONCE(cqe->res, res);
-		WRITE_ONCE(cqe->flags, cflags);
+		if (unlikely(req->flags & REQ_F_ZONE_APPEND)) {
+			if (likely(res > 0))
+				WRITE_ONCE(cqe->res64, req->rw.append_offset);
+			else
+				WRITE_ONCE(cqe->res64, res);
+		} else {
+			WRITE_ONCE(cqe->res, res);
+			WRITE_ONCE(cqe->flags, cflags);
+		}
 	} else if (ctx->cq_overflow_flushed) {
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1943,7 +1967,7 @@ static inline void req_set_fail_links(struct io_kiocb *req)
 		req->flags |= REQ_F_FAIL_LINK;
 }
 
-static void io_complete_rw_common(struct kiocb *kiocb, long res)
+static void io_complete_rw_common(struct kiocb *kiocb, long res, long long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
 	int cflags = 0;
@@ -1955,6 +1979,9 @@ static void io_complete_rw_common(struct kiocb *kiocb, long res)
 		req_set_fail_links(req);
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_kbuf(req);
+	if (req->flags & REQ_F_ZONE_APPEND)
+		req->rw.append_offset = res2;
+
 	__io_cqring_add_event(req, res, cflags);
 }
 
@@ -1962,7 +1989,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
 
-	io_complete_rw_common(kiocb, res);
+	io_complete_rw_common(kiocb, res, res2);
 	io_put_req(req);
 }
 
@@ -1976,8 +2003,11 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long long res2)
 	if (res != req->result)
 		req_set_fail_links(req);
 	req->result = res;
-	if (res != -EAGAIN)
+	if (res != -EAGAIN) {
+		if (req->flags & REQ_F_ZONE_APPEND)
+			req->rw.append_offset =  res2;
 		WRITE_ONCE(req->iopoll_completed, 1);
+	}
 }
 
 /*
@@ -2739,6 +2769,9 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
 						SB_FREEZE_WRITE);
 		}
 		kiocb->ki_flags |= IOCB_WRITE;
+		/* zone-append requires few extra steps during completion */
+		if (kiocb->ki_flags & IOCB_ZONE_APPEND)
+			req->flags |= REQ_F_ZONE_APPEND;
 
 		if (!force_nonblock)
 			current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92c2269..2580d93 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -156,8 +156,13 @@ enum {
  */
 struct io_uring_cqe {
 	__u64	user_data;	/* sqe->data submission passed back */
-	__s32	res;		/* result code for this event */
-	__u32	flags;
+	union {
+		struct {
+			__s32	res;	/* result code for this event */
+			__u32	flags;
+		};
+		__s64	res64;	/* appending offset for zone append */
+	};
 };
 
 /*
-- 
2.7.4