diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-07 08:52:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-07 08:52:43 -0700 |
commit | 0a78a376ef3c2f3d397df48909f00cd75f92137a (patch) | |
tree | 49a642a5ada33bf234247baae3ef9648de323caf /io_uring/io_uring.h | |
parent | 188943a15638ceb91f960e072ed7609b2d7f2a55 (diff) | |
parent | 108893ddcc4d3aa0a4a02aeb02d478e997001227 (diff) |
Merge tag 'for-6.1/io_uring-2022-10-03' of git://git.kernel.dk/linux
Pull io_uring updates from Jens Axboe:
- Add supported for more directly managed task_work running.
This is beneficial for real world applications that end up issuing
lots of system calls as part of handling work. Normal task_work will
always execute as we transition in and out of the kernel, even for
"unrelated" system calls. It's more efficient to defer the handling
of io_uring's deferred work until the application wants it to be run,
generally in batches.
As part of ongoing work to write an io_uring network backend for
Thrift, this has been shown to greatly improve performance. (Dylan)
- Add IOPOLL support for passthrough (Kanchan)
- Improvements and fixes to the send zero-copy support (Pavel)
- Partial IO handling fixes (Pavel)
- CQE ordering fixes around CQ ring overflow (Pavel)
- Support sendto() for non-zc as well (Pavel)
- Support sendmsg for zerocopy (Pavel)
- Networking iov_iter fix (Stefan)
- Misc fixes and cleanups (Pavel, me)
* tag 'for-6.1/io_uring-2022-10-03' of git://git.kernel.dk/linux: (56 commits)
io_uring/net: fix notif cqe reordering
io_uring/net: don't update msg_name if not provided
io_uring: don't gate task_work run on TIF_NOTIFY_SIGNAL
io_uring/rw: defer fsnotify calls to task context
io_uring/net: fix fast_iov assignment in io_setup_async_msg()
io_uring/net: fix non-zc send with address
io_uring/net: don't skip notifs for failed requests
io_uring/rw: don't lose short results on io_setup_async_rw()
io_uring/rw: fix unexpected link breakage
io_uring/net: fix cleanup double free free_iov init
io_uring: fix CQE reordering
io_uring/net: fix UAF in io_sendrecv_fail()
selftest/net: adjust io_uring sendzc notif handling
io_uring: ensure local task_work marks task as running
io_uring/net: zerocopy sendmsg
io_uring/net: combine fail handlers
io_uring/net: rename io_sendzc()
io_uring/net: support non-zerocopy sendto
io_uring/net: refactor io_setup_async_addr
io_uring/net: don't lose partial send_zc on fail
...
Diffstat (limited to 'io_uring/io_uring.h')
-rw-r--r-- | io_uring/io_uring.h | 62 |
1 files changed, 51 insertions, 11 deletions
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 2f73f83af960..48ce2348c8c1 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -24,9 +24,11 @@ enum { IOU_STOP_MULTISHOT = -ECANCELED, }; -struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx); +struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow); bool io_req_cqe_overflow(struct io_kiocb *req); -int io_run_task_work_sig(void); +int io_run_task_work_sig(struct io_ring_ctx *ctx); +int __io_run_local_work(struct io_ring_ctx *ctx, bool locked); +int io_run_local_work(struct io_ring_ctx *ctx); void io_req_complete_failed(struct io_kiocb *req, s32 res); void __io_req_complete(struct io_kiocb *req, unsigned issue_flags); void io_req_complete_post(struct io_kiocb *req); @@ -91,7 +93,8 @@ static inline void io_cq_lock(struct io_ring_ctx *ctx) void io_cq_unlock_post(struct io_ring_ctx *ctx); -static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx, + bool overflow) { if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { struct io_uring_cqe *cqe = ctx->cqe_cached; @@ -103,7 +106,12 @@ static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) return cqe; } - return __io_get_cqe(ctx); + return __io_get_cqe(ctx, overflow); +} + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +{ + return io_get_cqe_overflow(ctx, false); } static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx, @@ -221,17 +229,43 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; } -static inline bool io_run_task_work(void) +static inline int io_run_task_work(void) { - if (test_thread_flag(TIF_NOTIFY_SIGNAL)) { + if (task_work_pending(current)) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + clear_notify_signal(); __set_current_state(TASK_RUNNING); - clear_notify_signal(); - if (task_work_pending(current)) - task_work_run(); - return true; + task_work_run(); + return 1; } - return false; + return 0; +} + +static inline bool io_task_work_pending(struct io_ring_ctx *ctx) +{ + return test_thread_flag(TIF_NOTIFY_SIGNAL) || + !wq_list_empty(&ctx->work_llist); +} + +static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx) +{ + int ret = 0; + int ret2; + + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + ret = io_run_local_work(ctx); + + /* want to run this after in case more is added */ + ret2 = io_run_task_work(); + + /* Try propagate error in favour of if tasks were run, + * but still make sure to run them if requested + */ + if (ret >= 0) + ret += ret2; + + return ret; } static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) @@ -301,4 +335,10 @@ static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) return container_of(node, struct io_kiocb, comp_list); } +static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx) +{ + return likely(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN) || + ctx->submitter_task == current); +} + #endif |