io_uring: add support for 128-byte SQEs

Normal SQEs are 64-bytes in length, which is fine for all the commands
we support. However, in preparation for supporting passthrough IO,
provide an option for setting up a ring with 128-byte SQEs.

We continue to use the same type for io_uring_sqe, it's marked and
commented with a zero sized array pad at the end. This provides up
to 80 bytes of data for a passthrough command - 64 bytes for the
extra added data, and 16 bytes available at the end of the existing
SQE.

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

fs/io_uring.c

@@ -8519,8 +8519,12 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
 	 *    though the application is the one updating it.
 	 */
 	head = READ_ONCE(ctx->sq_array[sq_idx]);
-	if (likely(head < ctx->sq_entries))
+	if (likely(head < ctx->sq_entries)) {
+		/* double index for 128-byte SQEs, twice as long */
+		if (ctx->flags & IORING_SETUP_SQE128)
+			head <<= 1;
 		return &ctx->sq_sqes[head];
+	}
 
 	/* drop invalid entries */
 	ctx->cq_extra--;
@@ -11689,7 +11693,10 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 	rings->sq_ring_entries = p->sq_entries;
 	rings->cq_ring_entries = p->cq_entries;
 
-	size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
+	if (p->flags & IORING_SETUP_SQE128)
+		size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries);
+	else
+		size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
 	if (size == SIZE_MAX) {
 		io_mem_free(ctx->rings);
 		ctx->rings = NULL;
@@ -11933,7 +11940,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
 			IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL |
-			IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG))
+			IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG |
+			IORING_SETUP_SQE128))
 		return -EINVAL;
 
 	return io_uring_create(entries, &p, params);

include/uapi/linux/io_uring.h

@@ -63,6 +63,12 @@ struct io_uring_sqe {
 	};
 	__u64	addr3;
 	__u64	__pad2[1];
+
+	/*
+	 * If the ring is initialized with IORING_SETUP_SQE128, then this field
+	 * contains 64-bytes of padding, doubling the size of the SQE.
+	 */
+	__u64	__big_sqe_pad[0];
 };
 
 enum {
@@ -119,6 +125,8 @@ enum {
  */
 #define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
 
+#define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,