[PATCH 01/17] io_uring: add support for 128-byte SQEs

[Kanchan Joshi]

From: Jens Axboe <axboe at kernel.dk>

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 at kernel.dk>
---
 fs/io_uring.c                 | 13 ++++++++++---
 include/uapi/linux/io_uring.h |  7 +++++++
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a7412f6862fc..241ba1cd6dcf 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7431,8 +7431,12 @@ 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--;
@@ -10431,7 +10435,10 @@ 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;
@@ -10643,7 +10650,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
 			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
-			IORING_SETUP_R_DISABLED))
+			IORING_SETUP_R_DISABLED | IORING_SETUP_SQE128))
 		return -EINVAL;
 
 	return  io_uring_create(entries, &p, params);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 787f491f0d2a..c5db68433ca5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -61,6 +61,12 @@ struct io_uring_sqe {
 		__u32	file_index;
 	};
 	__u64	__pad2[2];
+
+	/*
+	 * If the ring is initializefd with IORING_SETUP_SQE128, then this field
+	 * contains 64-bytes of padding, doubling the size of the SQE.
+	 */
+	__u64	__big_sqe_pad[0];
 };
 
 enum {
@@ -101,6 +107,7 @@ enum {
 #define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
 #define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
 #define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
+#define IORING_SETUP_SQE128	(1U << 7)	/* SQEs are 128b */
 
 enum {
 	IORING_OP_NOP,
-- 
2.25.1