diff options
author | Christoph Müllner <christoph.muellner@vrull.eu> | 2025-08-01 13:55:33 +0200 |
---|---|---|
committer | Christoph Müllner <christophm30@gmail.com> | 2025-08-01 20:40:25 +0200 |
commit | 5d061c0ee23b1052d796e4e8e421aa6e16166fed (patch) | |
tree | 0ec5b8dceabfae236de0759c048b2a8fefad047f /linux-headers/include/linux/io_uring.h | |
parent | 686d7e6564509f1b25127df47e2f27a66958d0a0 (diff) | |
download | riscv-gnu-toolchain-master.zip riscv-gnu-toolchain-master.tar.gz riscv-gnu-toolchain-master.tar.bz2 |
This patch imports the Linux kernel headers v6.16.
This brings tons of new supported extensions for hwprobe.
Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Diffstat (limited to 'linux-headers/include/linux/io_uring.h')
-rw-r--r-- | linux-headers/include/linux/io_uring.h | 319 |
1 files changed, 304 insertions, 15 deletions
diff --git a/linux-headers/include/linux/io_uring.h b/linux-headers/include/linux/io_uring.h index 8e61f8b..cfd17e3 100644 --- a/linux-headers/include/linux/io_uring.h +++ b/linux-headers/include/linux/io_uring.h @@ -43,6 +43,10 @@ struct io_uring_sqe { union { __u64 addr; /* pointer to buffer or iovecs */ __u64 splice_off_in; + struct { + __u32 level; + __u32 optname; + }; }; __u32 len; /* buffer size or number of iovecs */ union { @@ -65,6 +69,11 @@ struct io_uring_sqe { __u32 xattr_flags; __u32 msg_ring_flags; __u32 uring_cmd_flags; + __u32 waitid_flags; + __u32 futex_flags; + __u32 install_fd_flags; + __u32 nop_flags; + __u32 pipe_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -79,16 +88,27 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + __u32 zcrx_ifq_idx; + __u32 optlen; struct { __u16 addr_len; __u16 __pad3[1]; }; + struct { + __u8 write_stream; + __u8 __pad4[3]; + }; }; union { struct { __u64 addr3; __u64 __pad2[1]; }; + struct { + __u64 attr_ptr; /* pointer to attribute information */ + __u64 attr_type_mask; /* bit mask of attributes */ + }; + __u64 optval; /* * If the ring is initialized with IORING_SETUP_SQE128, then * this field is used for 80 bytes of arbitrary command data @@ -97,6 +117,18 @@ struct io_uring_sqe { }; }; +/* sqe->attr_type_mask flags */ +#define IORING_RW_ATTR_FLAG_PI (1U << 0) +/* PI attribute information */ +struct io_uring_attr_pi { + __u16 flags; + __u16 app_tag; + __u32 len; + __u64 addr; + __u64 seed; + __u64 rsvd; +}; + /* * If sqe->file_index is set to this for opcodes that instantiate a new * direct descriptor (like openat/openat2/accept), then io_uring will allocate @@ -106,7 +138,7 @@ struct io_uring_sqe { */ #define IORING_FILE_INDEX_ALLOC (~0U) -enum { +enum io_uring_sqe_flags_bit { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, IOSQE_IO_LINK_BIT, @@ -190,6 +222,9 @@ enum { */ #define IORING_SETUP_NO_SQARRAY (1U << 16) +/* Use hybrid poll in iopoll process */ +#define IORING_SETUP_HYBRID_IOPOLL (1U << 17) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -240,19 +275,32 @@ enum io_uring_op { IORING_OP_URING_CMD, IORING_OP_SEND_ZC, IORING_OP_SENDMSG_ZC, + IORING_OP_READ_MULTISHOT, + IORING_OP_WAITID, + IORING_OP_FUTEX_WAIT, + IORING_OP_FUTEX_WAKE, + IORING_OP_FUTEX_WAITV, + IORING_OP_FIXED_FD_INSTALL, + IORING_OP_FTRUNCATE, + IORING_OP_BIND, + IORING_OP_LISTEN, + IORING_OP_RECV_ZC, + IORING_OP_EPOLL_WAIT, + IORING_OP_READV_FIXED, + IORING_OP_WRITEV_FIXED, + IORING_OP_PIPE, /* this goes last, obviously */ IORING_OP_LAST, }; /* - * sqe->uring_cmd_flags + * sqe->uring_cmd_flags top 8bits aren't available for userspace * IORING_URING_CMD_FIXED use registered buffer; pass this flag * along with setting sqe->buf_index. - * IORING_URING_CMD_POLLED driver use only */ #define IORING_URING_CMD_FIXED (1U << 0) -#define IORING_URING_CMD_POLLED (1U << 31) +#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED /* @@ -336,11 +384,20 @@ enum io_uring_op { * 0 is reported if zerocopy was actually possible. * IORING_NOTIF_USAGE_ZC_COPIED if data was copied * (at least partially). + * + * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send or + * recv will grab as many buffers from the buffer + * group ID given and send them all. The completion + * result will be the number of buffers send, with + * the starting buffer ID in cqe->flags as per + * usual for provided buffer usage. The buffers + * will be contiguous from the starting buffer ID. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) #define IORING_SEND_ZC_REPORT_USAGE (1U << 3) +#define IORING_RECVSEND_BUNDLE (1U << 4) /* * cqe.res for IORING_CQE_F_NOTIF if @@ -355,11 +412,13 @@ enum io_uring_op { * accept flags stored in sqe->ioprio */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +#define IORING_ACCEPT_DONTWAIT (1U << 1) +#define IORING_ACCEPT_POLL_FIRST (1U << 2) /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ -enum { +enum io_uring_msg_ring_flags { IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ IORING_MSG_SEND_FD, /* send a registered fd to another ring */ }; @@ -375,10 +434,27 @@ enum { #define IORING_MSG_RING_FLAGS_PASS (1U << 1) /* + * IORING_OP_FIXED_FD_INSTALL flags (sqe->install_fd_flags) + * + * IORING_FIXED_FD_NO_CLOEXEC Don't mark the fd as O_CLOEXEC + */ +#define IORING_FIXED_FD_NO_CLOEXEC (1U << 0) + +/* + * IORING_OP_NOP flags (sqe->nop_flags) + * + * IORING_NOP_INJECT_RESULT Inject result from sqe->result + */ +#define IORING_NOP_INJECT_RESULT (1U << 0) +#define IORING_NOP_FILE (1U << 1) +#define IORING_NOP_FIXED_FILE (1U << 2) +#define IORING_NOP_FIXED_BUFFER (1U << 3) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { - __u64 user_data; /* sqe->data submission passed back */ + __u64 user_data; /* sqe->user_data value passed back */ __s32 res; /* result code for this event */ __u32 flags; @@ -397,15 +473,23 @@ struct io_uring_cqe { * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv * IORING_CQE_F_NOTIF Set for notification CQEs. Can be used to distinct * them from sends. + * IORING_CQE_F_BUF_MORE If set, the buffer ID set in the completion will get + * more completions. In other words, the buffer is being + * partially consumed, and will be used by the kernel for + * more completions. This is only set for buffers used via + * the incremental buffer consumption, as provided by + * a ring buffer setup with IOU_PBUF_RING_INC. For any + * other provided buffer type, all completions with a + * buffer passed back is automatically returned to the + * application. */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) #define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) #define IORING_CQE_F_NOTIF (1U << 3) +#define IORING_CQE_F_BUF_MORE (1U << 4) -enum { - IORING_CQE_BUFFER_SHIFT = 16, -}; +#define IORING_CQE_BUFFER_SHIFT 16 /* * Magic offsets for the application to mmap the data it needs @@ -466,6 +550,9 @@ struct io_cqring_offsets { #define IORING_ENTER_SQ_WAIT (1U << 2) #define IORING_ENTER_EXT_ARG (1U << 3) #define IORING_ENTER_REGISTERED_RING (1U << 4) +#define IORING_ENTER_ABS_TIMER (1U << 5) +#define IORING_ENTER_EXT_ARG_REG (1U << 6) +#define IORING_ENTER_NO_IOWAIT (1U << 7) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -500,11 +587,15 @@ struct io_uring_params { #define IORING_FEAT_CQE_SKIP (1U << 11) #define IORING_FEAT_LINKED_FILE (1U << 12) #define IORING_FEAT_REG_REG_RING (1U << 13) +#define IORING_FEAT_RECVSEND_BUNDLE (1U << 14) +#define IORING_FEAT_MIN_TIMEOUT (1U << 15) +#define IORING_FEAT_RW_ATTR (1U << 16) +#define IORING_FEAT_NO_IOWAIT (1U << 17) /* * io_uring_register(2) opcodes and arguments */ -enum { +enum io_uring_register_op { IORING_REGISTER_BUFFERS = 0, IORING_UNREGISTER_BUFFERS = 1, IORING_REGISTER_FILES = 2, @@ -546,6 +637,29 @@ enum { /* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* return status information for a buffer group */ + IORING_REGISTER_PBUF_STATUS = 26, + + /* set/clear busy poll settings */ + IORING_REGISTER_NAPI = 27, + IORING_UNREGISTER_NAPI = 28, + + IORING_REGISTER_CLOCK = 29, + + /* clone registered buffers from source ring to current ring */ + IORING_REGISTER_CLONE_BUFFERS = 30, + + /* send MSG_RING without having a ring */ + IORING_REGISTER_SEND_MSG_RING = 31, + + /* register a netdev hw rx queue for zerocopy */ + IORING_REGISTER_ZCRX_IFQ = 32, + + /* resize CQ ring */ + IORING_REGISTER_RESIZE_RINGS = 33, + + IORING_REGISTER_MEM_REGION = 34, + /* this goes last */ IORING_REGISTER_LAST, @@ -554,7 +668,7 @@ enum { }; /* io-wq worker categories */ -enum { +enum io_wq_type { IO_WQ_BOUND, IO_WQ_UNBOUND, }; @@ -566,6 +680,31 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +enum { + /* initialise with user provided memory pointed by user_addr */ + IORING_MEM_REGION_TYPE_USER = 1, +}; + +struct io_uring_region_desc { + __u64 user_addr; + __u64 size; + __u32 flags; + __u32 id; + __u64 mmap_offset; + __u64 __resv[4]; +}; + +enum { + /* expose the region as registered wait arguments */ + IORING_MEM_REGION_REG_WAIT_ARG = 1, +}; + +struct io_uring_mem_region_reg { + __u64 region_uptr; /* struct io_uring_region_desc * */ + __u64 flags; + __u64 __resv[2]; +}; + /* * Register a fully sparse file space, rather than pass in an array of all * -1 file descriptors. @@ -626,6 +765,25 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_clock_register { + __u32 clockid; + __u32 __resv[3]; +}; + +enum { + IORING_REGISTER_SRC_REGISTERED = (1U << 0), + IORING_REGISTER_DST_REPLACE = (1U << 1), +}; + +struct io_uring_clone_buffers { + __u32 src_fd; + __u32 flags; + __u32 src_off; + __u32 dst_off; + __u32 nr; + __u32 pad[3]; +}; + struct io_uring_buf { __u64 addr; __u32 len; @@ -658,9 +816,17 @@ struct io_uring_buf_ring { * mmap(2) with the offset set as: * IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT) * to get a virtual mapping for the ring. + * IOU_PBUF_RING_INC: If set, buffers consumed from this buffer ring can be + * consumed incrementally. Normally one (or more) buffers + * are fully consumed. With incremental consumptions, it's + * feasible to register big ranges of buffers, and each + * use of it will consume only as much as it needs. This + * requires that both the kernel and application keep + * track of where the current read/recv index is at. */ -enum { +enum io_uring_register_pbuf_ring_flags { IOU_PBUF_RING_MMAP = 1, + IOU_PBUF_RING_INC = 2, }; /* argument for IORING_(UN)REGISTER_PBUF_RING */ @@ -672,10 +838,53 @@ struct io_uring_buf_reg { __u64 resv[3]; }; +/* argument for IORING_REGISTER_PBUF_STATUS */ +struct io_uring_buf_status { + __u32 buf_group; /* input */ + __u32 head; /* output */ + __u32 resv[8]; +}; + +enum io_uring_napi_op { + /* register/ungister backward compatible opcode */ + IO_URING_NAPI_REGISTER_OP = 0, + + /* opcodes to update napi_list when static tracking is used */ + IO_URING_NAPI_STATIC_ADD_ID = 1, + IO_URING_NAPI_STATIC_DEL_ID = 2 +}; + +enum io_uring_napi_tracking_strategy { + /* value must be 0 for backward compatibility */ + IO_URING_NAPI_TRACKING_DYNAMIC = 0, + IO_URING_NAPI_TRACKING_STATIC = 1, + IO_URING_NAPI_TRACKING_INACTIVE = 255 +}; + +/* argument for IORING_(UN)REGISTER_NAPI */ +struct io_uring_napi { + __u32 busy_poll_to; + __u8 prefer_busy_poll; + + /* a io_uring_napi_op value */ + __u8 opcode; + __u8 pad[2]; + + /* + * for IO_URING_NAPI_REGISTER_OP, it is a + * io_uring_napi_tracking_strategy value. + * + * for IO_URING_NAPI_STATIC_ADD_ID/IO_URING_NAPI_STATIC_DEL_ID + * it is the napi id to add/del from napi_list. + */ + __u32 op_param; + __u32 resv; +}; + /* * io_uring_restriction->opcode values */ -enum { +enum io_uring_register_restriction_op { /* Allow an io_uring_register(2) opcode */ IORING_RESTRICTION_REGISTER_OP = 0, @@ -691,10 +900,33 @@ enum { IORING_RESTRICTION_LAST }; +enum { + IORING_REG_WAIT_TS = (1U << 0), +}; + +/* + * Argument for io_uring_enter(2) with + * IORING_GETEVENTS | IORING_ENTER_EXT_ARG_REG set, where the actual argument + * is an index into a previously registered fixed wait region described by + * the below structure. + */ +struct io_uring_reg_wait { + struct __kernel_timespec ts; + __u32 min_wait_usec; + __u32 flags; + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad[3]; + __u64 pad2[2]; +}; + +/* + * Argument for io_uring_enter(2) with IORING_GETEVENTS | IORING_ENTER_EXT_ARG + */ struct io_uring_getevents_arg { __u64 sigmask; __u32 sigmask_sz; - __u32 pad; + __u32 min_wait_usec; __u64 ts; }; @@ -731,9 +963,66 @@ struct io_uring_recvmsg_out { /* * Argument for IORING_OP_URING_CMD when file is a socket */ -enum { +enum io_uring_socket_op { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, + SOCKET_URING_OP_GETSOCKOPT, + SOCKET_URING_OP_SETSOCKOPT, +}; + +/* Zero copy receive refill queue entry */ +struct io_uring_zcrx_rqe { + __u64 off; + __u32 len; + __u32 __pad; +}; + +struct io_uring_zcrx_cqe { + __u64 off; + __u64 __pad; +}; + +/* The bit from which area id is encoded into offsets */ +#define IORING_ZCRX_AREA_SHIFT 48 +#define IORING_ZCRX_AREA_MASK (~(((__u64)1 << IORING_ZCRX_AREA_SHIFT) - 1)) + +struct io_uring_zcrx_offsets { + __u32 head; + __u32 tail; + __u32 rqes; + __u32 __resv2; + __u64 __resv[2]; +}; + +enum io_uring_zcrx_area_flags { + IORING_ZCRX_AREA_DMABUF = 1, +}; + +struct io_uring_zcrx_area_reg { + __u64 addr; + __u64 len; + __u64 rq_area_token; + __u32 flags; + __u32 dmabuf_fd; + __u64 __resv2[2]; +}; + +/* + * Argument for IORING_REGISTER_ZCRX_IFQ + */ +struct io_uring_zcrx_ifq_reg { + __u32 if_idx; + __u32 if_rxq; + __u32 rq_entries; + __u32 flags; + + __u64 area_ptr; /* pointer to struct io_uring_zcrx_area_reg */ + __u64 region_ptr; /* struct io_uring_region_desc * */ + + struct io_uring_zcrx_offsets offsets; + __u32 zcrx_id; + __u32 __resv2; + __u64 __resv[3]; }; #ifdef __cplusplus |