io_uring.h: add IORING_SETUP_SQE128 and IORING_SETUP_CQE32

This asks the kernel to setup a ring with 128-byte SQE and
32-byte CQE entries. It may fail with -EINVAL if the kernel
doesn't support this feature. If the kernel does support this
feature, then the ring will support big-sqe/big-cqe entries
which some commands may require.

Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Link: https://lore.kernel.org/r/20220531133155.17493-2-ankit.kumar@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/os/linux/io_uring.h b/os/linux/io_uring.h
index 42b2fe84dbcd53bfd2454c80cc1685cdabcab54e..2fa661350b63ecabad3f91ce191ea616e398695a 100644 (file)
--- a/os/linux/io_uring.h
+++ b/os/linux/io_uring.h
@@ -60,7 +60,17 @@ struct io_uring_sqe {
                __s32   splice_fd_in;
                __u32   file_index;
        };
-       __u64   __pad2[2];
+       union {
+               struct {
+                       __u64   addr3;
+                       __u64   __pad2[1];
+               };
+               /*
+                * If the ring is initialized with IORING_SETUP_SQE128, then
+                * this field is used for 80 bytes of arbitrary command data
+                */
+               __u8    cmd[0];
+       };
 };
 
 enum {
@@ -101,6 +111,24 @@ 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_SUBMIT_ALL        (1U << 7)       /* continue submit on error */
+/*
+ * Cooperative task running. When requests complete, they often require
+ * forcing the submitter to transition to the kernel to complete. If this
+ * flag is set, work will be done when the task transitions anyway, rather
+ * than force an inter-processor interrupt reschedule. This avoids interrupting
+ * a task running in userspace, and saves an IPI.
+ */
+#define IORING_SETUP_COOP_TASKRUN      (1U << 8)
+/*
+ * If COOP_TASKRUN is set, get notified if task work is available for
+ * running and a kernel transition would be needed to run it. This sets
+ * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
+ */
+#define IORING_SETUP_TASKRUN_FLAG      (1U << 9)
+
+#define IORING_SETUP_SQE128            (1U << 10) /* SQEs are 128 byte */
+#define IORING_SETUP_CQE32             (1U << 11) /* CQEs are 32 byte */
 
 enum {
        IORING_OP_NOP,
@@ -192,6 +220,12 @@ struct io_uring_cqe {
        __u64   user_data;      /* sqe->data submission passed back */
        __s32   res;            /* result code for this event */
        __u32   flags;
+
+       /*
+        * If the ring is initialized with IORING_SETUP_CQE32, then this field
+        * contains 16-bytes of padding, doubling the size of the CQE.
+        */
+       __u64 big_cqe[];
 };
 
 /*