view release on metacpan or  search on metacpan

libev/ev_iouring.c  view on Meta::CPAN

/*
 * libev linux io_uring fd activity backend
 *
 * Copyright (c) 2019-2020 Marc Alexander Lehmann <libev@schmorp.de>
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modifica-
 * tion, are permitted provided that the following conditions are met:
 *
 *   1.  Redistributions of source code must retain the above copyright notice,
 *       this list of conditions and the following disclaimer.
 *
 *   2.  Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in the
 *       documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
 * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
 * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
 * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
 * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
 * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
 * OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Alternatively, the contents of this file may be used under the terms of
 * the GNU General Public License ("GPL") version 2 or any later version,
 * in which case the provisions of the GPL are applicable instead of
 * the above. If you wish to allow the use of your version of this file
 * only under the terms of the GPL and not to allow others to use your
 * version of this file under the BSD license, indicate your decision
 * by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL. If you do not delete the
 * provisions above, a recipient may use your version of this file under
 * either the BSD or the GPL.
 */

/*
 * general notes about linux io_uring:
 *
 * a) it's the best interface I have seen so far. on linux.
 * b) best is not necessarily very good.
 * c) it's better than the aio mess, doesn't suffer from the fork problems
 *    of linux aio or epoll and so on and so on. and you could do event stuff
 *    without any syscalls. what's not to like?
 * d) ok, it's vastly more complex, but that's ok, really.
 * e) why two mmaps instead of one? one would be more space-efficient,
 *    and I can't see what benefit two would have (other than being
 *    somehow resizable/relocatable, but that's apparently not possible).
 * f) hmm, it's practically undebuggable (gdb can't access the memory, and
 *    the bizarre way structure offsets are communicated makes it hard to
 *    just print the ring buffer heads, even *iff* the memory were visible
 *    in gdb. but then, that's also ok, really.
 * g) well, you cannot specify a timeout when waiting for events. no,
 *    seriously, the interface doesn't support a timeout. never seen _that_
 *    before. sure, you can use a timerfd, but that's another syscall
 *    you could have avoided. overall, this bizarre omission smells
 *    like a µ-optimisation by the io_uring author for his personal
 *    applications, to the detriment of everybody else who just wants
 *    an event loop. but, umm, ok, if that's all, it could be worse.
 *    (from what I gather from the author Jens Axboe, it simply didn't
 *    occur to him, and he made good on it by adding an unlimited number
 *    of timeouts later :).
 * h) initially there was a hardcoded limit of 4096 outstanding events.
 *    later versions not only bump this to 32k, but also can handle
 *    an unlimited amount of events, so this only affects the batch size.
 * i) unlike linux aio, you *can* register more then the limit
 *    of fd events. while early versions of io_uring signalled an overflow
 *    and you ended up getting wet. 5.5+ does not do this anymore.
 * j) but, oh my! it had exactly the same bugs as the linux aio backend,
 *    where some undocumented poll combinations just fail. fortunately,
 *    after finally reaching the author, he was more than willing to fix
 *    this probably in 5.6+.
 * k) overall, the *API* itself is, I dare to say, not a total trainwreck.
 *    once the bugs ae fixed (probably in 5.6+), it will be without
 *    competition.
 */

/* TODO: use internal TIMEOUT */
/* TODO: take advantage of single mmap, NODROP etc. */
/* TODO: resize cq/sq size independently */

#include <sys/timerfd.h>
#include <sys/mman.h>
#include <poll.h>
#include <stdint.h>

#define IOURING_INIT_ENTRIES 32

/*****************************************************************************/
/* syscall wrapdadoop - this section has the raw api/abi definitions */

#include <linux/fs.h>
#include <linux/types.h>

/* mostly directly taken from the kernel or documentation */

struct io_uring_sqe
{
  __u8 opcode;
  __u8 flags;
  __u16 ioprio;
  __s32 fd;
  union {
    __u64 off;
    __u64 addr2;
  };
  __u64 addr;
  __u32 len;