Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 15 6月, 2020 1 次提交
    • P
      io_uring: fix lazy work init · 59960b9d
      由 Pavel Begunkov 提交于 
      Don't leave garbage in req.work before punting async on -EAGAIN
in io_iopoll_queue().

[  140.922099] general protection fault, probably for non-canonical
     address 0xdead000000000100: 0000 [#1] PREEMPT SMP PTI
...
[  140.922105] RIP: 0010:io_worker_handle_work+0x1db/0x480
...
[  140.922114] Call Trace:
[  140.922118]  ? __next_timer_interrupt+0xe0/0xe0
[  140.922119]  io_wqe_worker+0x2a9/0x360
[  140.922121]  ? _raw_spin_unlock_irqrestore+0x24/0x40
[  140.922124]  kthread+0x12c/0x170
[  140.922125]  ? io_worker_handle_work+0x480/0x480
[  140.922126]  ? kthread_park+0x90/0x90
[  140.922127]  ret_from_fork+0x22/0x30

Fixes: 7cdaf587 ("io_uring: avoid whole io_wq_work copy for requests completed inline")
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      59960b9d
  3. 11 6月, 2020 7 次提交
  5. 10 6月, 2020 2 次提交
  7. 09 6月, 2020 4 次提交
  9. 08 6月, 2020 2 次提交
  11. 05 6月, 2020 5 次提交
  13. 03 6月, 2020 1 次提交
    • J
      io_uring: disallow close of ring itself · fd2206e4
      由 Jens Axboe 提交于 
      A previous commit enabled this functionality, which also enabled O_PATH
to work correctly with io_uring. But we can't safely close the ring
itself, as the file handle isn't reference counted inside
io_uring_enter(). Instead of jumping through hoops to enable ring
closure, add a "soft" ->needs_file option, ->needs_file_no_error. This
enables O_PATH file descriptors to work, but still catches the case of
trying to close the ring itself.
Reported-by: NJann Horn <jannh@google.com>
Fixes: 904fbcb1 ("io_uring: remove 'fd is io_uring' from close path")
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      fd2206e4
  15. 30 5月, 2020 3 次提交
  17. 27 5月, 2020 7 次提交
  19. 20 5月, 2020 4 次提交
    • X
      io_uring: don't submit sqes when ctx->refs is dying · 6b668c9b
      由 Xiaoguang Wang 提交于 
      When IORING_SETUP_SQPOLL is enabled, io_ring_ctx_wait_and_kill() will wait
for sq thread to idle by busy loop:

    while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
        cond_resched();

Above loop isn't very CPU friendly, it may introduce a short cpu burst on
the current cpu.

If ctx->refs is dying, we forbid sq_thread from submitting any further
SQEs. Instead they just get discarded when we exit.
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      6b668c9b
    • X
      io_uring: reset -EBUSY error when io sq thread is waken up · d4ae271d
      由 Xiaoguang Wang 提交于 
      In io_sq_thread(), currently if we get an -EBUSY error and go to sleep,
we will won't clear it again, which will result in io_sq_thread() will
never have a chance to submit sqes again. Below test program test.c
can reveal this bug:

int main(int argc, char *argv[])
{
        struct io_uring ring;
        int i, fd, ret;
        struct io_uring_sqe *sqe;
        struct io_uring_cqe *cqe;
        struct iovec *iovecs;
        void *buf;
        struct io_uring_params p;

        if (argc < 2) {
                printf("%s: file\n", argv[0]);
                return 1;
        }

        memset(&p, 0, sizeof(p));
        p.flags = IORING_SETUP_SQPOLL;
        ret = io_uring_queue_init_params(4, &ring, &p);
        if (ret < 0) {
                fprintf(stderr, "queue_init: %s\n", strerror(-ret));
                return 1;
        }

        fd = open(argv[1], O_RDONLY | O_DIRECT);
        if (fd < 0) {
                perror("open");
                return 1;
        }

        iovecs = calloc(10, sizeof(struct iovec));
        for (i = 0; i < 10; i++) {
                if (posix_memalign(&buf, 4096, 4096))
                        return 1;
                iovecs[i].iov_base = buf;
                iovecs[i].iov_len = 4096;
        }

        ret = io_uring_register_files(&ring, &fd, 1);
        if (ret < 0) {
                fprintf(stderr, "%s: register %d\n", __FUNCTION__, ret);
                return ret;
        }

        for (i = 0; i < 10; i++) {
                sqe = io_uring_get_sqe(&ring);
                if (!sqe)
                        break;

                io_uring_prep_readv(sqe, 0, &iovecs[i], 1, 0);
                sqe->flags |= IOSQE_FIXED_FILE;

                ret = io_uring_submit(&ring);
                sleep(1);
                printf("submit %d\n", i);
        }

        for (i = 0; i < 10; i++) {
                io_uring_wait_cqe(&ring, &cqe);
                printf("receive: %d\n", i);
                if (cqe->res != 4096) {
                        fprintf(stderr, "ret=%d, wanted 4096\n", cqe->res);
                        ret = 1;
                }
                io_uring_cqe_seen(&ring, cqe);
        }

        close(fd);
        io_uring_queue_exit(&ring);
        return 0;
}
sudo ./test testfile
above command will hang on the tenth request, to fix this bug, when io
sq_thread is waken up, we reset the variable 'ret' to be zero.
Suggested-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      d4ae271d
    • J
      io_uring: don't add non-IO requests to iopoll pending list · b532576e
      由 Jens Axboe 提交于 
      We normally disable any commands that aren't specifically poll commands
for a ring that is setup for polling, but we do allow buffer provide and
remove commands to support buffer selection for polled IO. Once a
request is issued, we add it to the poll list to poll for completion. But
we should not do that for non-IO commands, as those request complete
inline immediately and aren't pollable. If we do, we can leave requests
on the iopoll list after they are freed.

Fixes: ddf0322d ("io_uring: add IORING_OP_PROVIDE_BUFFERS")
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      b532576e
    • B
      io_uring: don't use kiocb.private to store buf_index · 4f4eeba8
      由 Bijan Mottahedeh 提交于 
      kiocb.private is used in iomap_dio_rw() so store buf_index separately.
Signed-off-by: NBijan Mottahedeh <bijan.mottahedeh@oracle.com>

Move 'buf_index' to a hole in io_kiocb.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      4f4eeba8
  21. 19 5月, 2020 1 次提交
    • J
      io_uring: cancel work if task_work_add() fails · e3aabf95
      由 Jens Axboe 提交于 
      We currently move it to the io_wqe_manager for execution, but we cannot
safely do so as we may lack some of the state to execute it out of
context. As we cancel work anyway when the ring/task exits, just mark
this request as canceled and io_async_task_func() will do the right
thing.

Fixes: aa96bf8a ("io_uring: use io-wq manager as backup task if task is exiting")
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      e3aabf95
  23. 18 5月, 2020 3 次提交