Merge tag 'for-5.19/io_uring-2022-05-22' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Here are the main io_uring changes for 5.19. This contains:

   - Fixes for sparse type warnings (Christoph, Vasily)

   - Support for multi-shot accept (Hao)

   - Support for io_uring managed fixed files, rather than always
     needing the applicationt o manage the indices (me)

   - Fix for a spurious poll wakeup (Dylan)

   - CQE overflow fixes (Dylan)

   - Support more types of cancelations (me)

   - Support for co-operative task_work signaling, rather than always
     forcing an IPI (me)

   - Support for doing poll first when appropriate, rather than always
     attempting a transfer first (me)

   - Provided buffer cleanups and support for mapped buffers (me)

   - Improve how io_uring handles inflight SCM files (Pavel)

   - Speedups for registered files (Pavel, me)

   - Organize the completion data in a struct in io_kiocb rather than
     keep it in separate spots (Pavel)

   - task_work improvements (Pavel)

   - Cleanup and optimize the submission path, in general and for
     handling links (Pavel)

   - Speedups for registered resource handling (Pavel)

   - Support sparse buffers and file maps (Pavel, me)

   - Various fixes and cleanups (Almog, Pavel, me)"

* tag 'for-5.19/io_uring-2022-05-22' of git://git.kernel.dk/linux-block: (111 commits)
  io_uring: fix incorrect __kernel_rwf_t cast
  io_uring: disallow mixed provided buffer group registrations
  io_uring: initialize io_buffer_list head when shared ring is unregistered
  io_uring: add fully sparse buffer registration
  io_uring: use rcu_dereference in io_close
  io_uring: consistently use the EPOLL* defines
  io_uring: make apoll_events a __poll_t
  io_uring: drop a spurious inline on a forward declaration
  io_uring: don't use ERR_PTR for user pointers
  io_uring: use a rwf_t for io_rw.flags
  io_uring: add support for ring mapped supplied buffers
  io_uring: add io_pin_pages() helper
  io_uring: add buffer selection support to IORING_OP_NOP
  io_uring: fix locking state for empty buffer group
  io_uring: implement multishot mode for accept
  io_uring: let fast poll support multishot
  io_uring: add REQ_F_APOLL_MULTISHOT for requests
  io_uring: add IORING_ACCEPT_MULTISHOT for accept
  io_uring: only wake when the correct events are set
  io_uring: avoid io-wq -EAGAIN looping for !IOPOLL
  ...
This commit is contained in:
Linus Torvalds
2022-05-23 12:22:49 -07:00
8 changed files with 1818 additions and 1036 deletions

View File

@@ -63,6 +63,15 @@ struct io_uring_sqe {
__u64 __pad2[2];
};
/*
* 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
* an available direct descriptor instead of having the application pass one
* in. The picked direct descriptor will be returned in cqe->res, or -ENFILE
* if the space is full.
*/
#define IORING_FILE_INDEX_ALLOC (~0U)
enum {
IOSQE_FIXED_FILE_BIT,
IOSQE_IO_DRAIN_BIT,
@@ -102,6 +111,20 @@ enum {
#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)
enum {
IORING_OP_NOP,
@@ -187,6 +210,33 @@ enum {
#define IORING_POLL_UPDATE_EVENTS (1U << 1)
#define IORING_POLL_UPDATE_USER_DATA (1U << 2)
/*
* ASYNC_CANCEL flags.
*
* IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key
* IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the
* request 'user_data'
* IORING_ASYNC_CANCEL_ANY Match any request
*/
#define IORING_ASYNC_CANCEL_ALL (1U << 0)
#define IORING_ASYNC_CANCEL_FD (1U << 1)
#define IORING_ASYNC_CANCEL_ANY (1U << 2)
/*
* send/sendmsg and recv/recvmsg flags (sqe->addr2)
*
* IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send
* or receive and arm poll if that yields an
* -EAGAIN result, arm poll upfront and skip
* the initial transfer attempt.
*/
#define IORING_RECVSEND_POLL_FIRST (1U << 0)
/*
* accept flags stored in sqe->ioprio
*/
#define IORING_ACCEPT_MULTISHOT (1U << 0)
/*
* IO completion data structure (Completion Queue Entry)
*/
@@ -236,6 +286,7 @@ struct io_sqring_offsets {
*/
#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */
#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */
#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */
struct io_cqring_offsets {
__u32 head;
@@ -333,6 +384,10 @@ enum {
IORING_REGISTER_RING_FDS = 20,
IORING_UNREGISTER_RING_FDS = 21,
/* register ring based provide buffer group */
IORING_REGISTER_PBUF_RING = 22,
IORING_UNREGISTER_PBUF_RING = 23,
/* this goes last */
IORING_REGISTER_LAST
};
@@ -350,9 +405,15 @@ struct io_uring_files_update {
__aligned_u64 /* __s32 * */ fds;
};
/*
* Register a fully sparse file space, rather than pass in an array of all
* -1 file descriptors.
*/
#define IORING_RSRC_REGISTER_SPARSE (1U << 0)
struct io_uring_rsrc_register {
__u32 nr;
__u32 resv;
__u32 flags;
__u64 resv2;
__aligned_u64 data;
__aligned_u64 tags;
@@ -404,6 +465,38 @@ struct io_uring_restriction {
__u32 resv2[3];
};
struct io_uring_buf {
__u64 addr;
__u32 len;
__u16 bid;
__u16 resv;
};
struct io_uring_buf_ring {
union {
/*
* To avoid spilling into more pages than we need to, the
* ring tail is overlaid with the io_uring_buf->resv field.
*/
struct {
__u64 resv1;
__u32 resv2;
__u16 resv3;
__u16 tail;
};
struct io_uring_buf bufs[0];
};
};
/* argument for IORING_(UN)REGISTER_PBUF_RING */
struct io_uring_buf_reg {
__u64 ring_addr;
__u32 ring_entries;
__u16 bgid;
__u16 pad;
__u64 resv[3];
};
/*
* io_uring_restriction->opcode values
*/