io_uring: introduce non-circular SQ

Outside of SQPOLL, normally SQ entries are consumed by the time the
submission syscall returns. For those cases we don't need a circular
buffer and the head/tail tracking, instead the kernel can assume that
entries always start from the beginning of the SQ at index 0. This patch
introduces a setup flag doing exactly that. It's a simpler and helps
to keeps SQEs hot in cache.

The feature is optional and enabled by setting IORING_SETUP_SQ_REWIND.
The flag is rejected if passed together with SQPOLL as it'd require
waiting for SQ before each submission. It also requires
IORING_SETUP_NO_SQARRAY, which can be supported but it's unlikely there
will be users, so leave more space for future optimisations.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 36 insertions, 8 deletions

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index b5b23c0d5283..475094c7a668 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -237,6 +237,18 @@ enum io_uring_sqe_flags_bit {
  */
 #define IORING_SETUP_SQE_MIXED		(1U << 19)
 
+/*
+ * When set, io_uring ignores SQ head and tail and fetches SQEs to submit
+ * starting from index 0 instead from the index stored in the head pointer.
+ * IOW, the user should place all SQE at the beginning of the SQ memory
+ * before issuing a submission syscall.
+ *
+ * It requires IORING_SETUP_NO_SQARRAY and is incompatible with
+ * IORING_SETUP_SQPOLL. The user must also never change the SQ head and tail
+ * values and keep it set to 0. Any other value is undefined behaviour.
+ */
+#define IORING_SETUP_SQ_REWIND		(1U << 20)
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index a50459238bee..0f88ec74e55d 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1945,12 +1945,16 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
 
-	/*
-	 * Ensure any loads from the SQEs are done at this point,
-	 * since once we write the new head, the application could
-	 * write new data to them.
-	 */
-	smp_store_release(&rings->sq.head, ctx->cached_sq_head);
+	if (ctx->flags & IORING_SETUP_SQ_REWIND) {
+		ctx->cached_sq_head = 0;
+	} else {
+		/*
+		 * Ensure any loads from the SQEs are done at this point,
+		 * since once we write the new head, the application could
+		 * write new data to them.
+		 */
+		smp_store_release(&rings->sq.head, ctx->cached_sq_head);
+	}
 }
 
 /*
@@ -1996,10 +2000,15 @@ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
 int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	__must_hold(&ctx->uring_lock)
 {
-	unsigned int entries = io_sqring_entries(ctx);
+	unsigned int entries;
 	unsigned int left;
 	int ret;
 
+	if (ctx->flags & IORING_SETUP_SQ_REWIND)
+		entries = ctx->sq_entries;
+	else
+		entries = io_sqring_entries(ctx);
+
 	entries = min(nr, entries);
 	if (unlikely(!entries))
 		return 0;
@@ -2728,6 +2737,12 @@ static int io_uring_sanitise_params(struct io_uring_params *p)
 	if (flags & ~IORING_SETUP_FLAGS)
 		return -EINVAL;
 
+	if (flags & IORING_SETUP_SQ_REWIND) {
+		if ((flags & IORING_SETUP_SQPOLL) ||
+		    !(flags & IORING_SETUP_NO_SQARRAY))
+		return -EINVAL;
+	}
+
 	/* There is no way to mmap rings without a real fd */
 	if ((flags & IORING_SETUP_REGISTERED_FD_ONLY) &&
 	    !(flags & IORING_SETUP_NO_MMAP))
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 29b8f90fdabf..acdc39b9f8d6 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -69,7 +69,8 @@ struct io_ctx_config {
 			IORING_SETUP_NO_SQARRAY |\
 			IORING_SETUP_HYBRID_IOPOLL |\
 			IORING_SETUP_CQE_MIXED |\
-			IORING_SETUP_SQE_MIXED)
+			IORING_SETUP_SQE_MIXED |\
+			IORING_SETUP_SQ_REWIND)
 
 #define IORING_ENTER_FLAGS (IORING_ENTER_GETEVENTS |\
 			IORING_ENTER_SQ_WAKEUP |\