sqe->flags is u8, and now we have used 7 bits, so take the last one for
extending purpose.
If bit7(IOSQE_HAS_EXT_FLAGS_BIT) is 1, it means this sqe carries ext flags
from the last byte(.ext_flags), or bit23~bit16 of sqe->uring_cmd_flags for
IORING_OP_URING_CMD.
io_slot_flags() return value is converted to `ULL` because the affected bits
are beyond 32bit now.
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
include/linux/io_uring_types.h | 6 ++++--
include/uapi/linux/io_uring.h | 13 +++++++++++++
io_uring/filetable.h | 2 +-
io_uring/io_uring.c | 14 +++++++++++++-
io_uring/uring_cmd.c | 3 ++-
5 files changed, 33 insertions(+), 5 deletions(-)
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3e72fa52f1e3..67347e5d06ec 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -435,6 +435,7 @@ struct io_tw_state {
};
enum {
+ /* 1st byte is from sqe->flags, and 2nd is from sqe ext_flags */
REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT,
REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT,
REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT,
@@ -442,9 +443,10 @@ enum {
REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT,
+ REQ_F_SQE_EXT_FLAGS_BIT = IOSQE_HAS_EXT_FLAGS_BIT,
- /* first byte is taken by user flags, shift it to not overlap */
- REQ_F_FAIL_BIT = 8,
+ /* first 2 bytes are taken by user flags, shift it to not overlap */
+ REQ_F_FAIL_BIT = 16,
REQ_F_INFLIGHT_BIT,
REQ_F_CUR_POS_BIT,
REQ_F_NOWAIT_BIT,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a7f847543a7f..4847d7cf1ac9 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -98,6 +98,10 @@ struct io_uring_sqe {
__u64 __pad2[1];
};
__u64 optval;
+ struct {
+ __u8 __pad4[15];
+ __u8 ext_flags;
+ };
/*
* If the ring is initialized with IORING_SETUP_SQE128, then
* this field is used for 80 bytes of arbitrary command data
@@ -123,6 +127,7 @@ enum io_uring_sqe_flags_bit {
IOSQE_ASYNC_BIT,
IOSQE_BUFFER_SELECT_BIT,
IOSQE_CQE_SKIP_SUCCESS_BIT,
+ IOSQE_HAS_EXT_FLAGS_BIT,
};
/*
@@ -142,6 +147,11 @@ enum io_uring_sqe_flags_bit {
#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT)
/* don't post CQE if request succeeded */
#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
+/*
+ * sqe ext flags carried in the last byte, or bit23~bit16 of
+ * sqe->uring_cmd_flags for IORING_URING_CMD.
+ */
+#define IOSQE_HAS_EXT_FLAGS (1U << IOSQE_HAS_EXT_FLAGS_BIT)
/*
* io_uring_setup() flags
@@ -263,11 +273,14 @@ enum io_uring_op {
/*
* sqe->uring_cmd_flags top 8bits aren't available for userspace
+ * bit31 ~ bit24 kernel internal usage
+ * bit23 ~ bit16 sqe ext flags
* IORING_URING_CMD_FIXED use registered buffer; pass this flag
* along with setting sqe->buf_index.
*/
#define IORING_URING_CMD_FIXED (1U << 0)
#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED
+#define IORING_URING_CMD_EXT_MASK 0x00ff0000
/*
diff --git a/io_uring/filetable.h b/io_uring/filetable.h
index b2435c4dca1f..d25247c9b9f5 100644
--- a/io_uring/filetable.h
+++ b/io_uring/filetable.h
@@ -43,7 +43,7 @@ io_fixed_file_slot(struct io_file_table *table, unsigned i)
#define FFS_ISREG 0x2UL
#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG)
-static inline unsigned int io_slot_flags(struct io_fixed_file *slot)
+static inline unsigned long io_slot_flags(struct io_fixed_file *slot)
{
return (slot->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT;
}
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8df9ad010803..6d4def11aebf 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -109,7 +109,8 @@
IOSQE_IO_HARDLINK | IOSQE_ASYNC)
#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
- IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
+ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS | \
+ IOSQE_HAS_EXT_FLAGS)
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
@@ -2080,6 +2081,17 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
/* enforce forwards compatibility on users */
if (sqe_flags & ~SQE_VALID_FLAGS)
return io_init_fail_req(req, -EINVAL);
+ if (sqe_flags & IOSQE_HAS_EXT_FLAGS) {
+ u32 sqe_ext_flags;
+
+ if (opcode != IORING_OP_URING_CMD)
+ sqe_ext_flags = READ_ONCE(sqe->ext_flags);
+ else
+ sqe_ext_flags = (READ_ONCE(sqe->uring_cmd_flags)
+ & IORING_URING_CMD_EXT_MASK) >> 16;
+ req->flags |= sqe_ext_flags << 8;
+ }
+
if (sqe_flags & IOSQE_BUFFER_SELECT) {
if (!def->buffer_select)
return io_init_fail_req(req, -EOPNOTSUPP);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 334d31dd6628..43b71f29e7b3 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -202,7 +202,8 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (sqe->__pad1)
return -EINVAL;
- ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags);
+ ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags) &
+ ~IORING_URING_CMD_EXT_MASK;
if (ioucmd->flags & ~IORING_URING_CMD_MASK)
return -EINVAL;
--
2.42.0
